{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/alphazero","slug":"alphazero","name":"AlphaZero","full_name":"AlphaZero","full_name_withheld":false,"description_markdown":"**AlphaZero** is a reinforcement learning agent for playing board games such as Go, chess, and shogi. ","description_state":"present","introduced_year":null,"introduced_by":{"title":"Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm","paper":"/paper/mastering-chess-and-shogi-by-self-play-with-a","first_author":"David Silver","n_authors":13,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/mastering-chess-and-shogi-by-self-play-with-a"},"source":{"url":"http://arxiv.org/abs/1712.01815v1","title":"Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Reinforcement Learning","area_id":"reinforcement-learning","collection":"Board Game Models","url":"/methods/category/board-game-models","pwc_aliases":[]}],"n_papers_tagged":114,"archive_num_papers":114,"papers_newest_first":[{"paper":"/paper/alphazero-edu-making-alphazero-accessible-to","slug":"alphazero-edu-making-alphazero-accessible-to","title":"AlphaZero-Edu: Making AlphaZero Accessible to Everyone","date":"2025-04-20","arxiv_id":"2504.14636","n_code_links":1,"syntology":null},{"paper":"/paper/assistancezero-scalably-solving-assistance","slug":"assistancezero-scalably-solving-assistance","title":"AssistanceZero: Scalably Solving Assistance Games","date":"2025-04-09","arxiv_id":"2504.07091","n_code_links":1,"syntology":null},{"paper":null,"slug":"rotated-bitboards-in-fusc-and-reinforcement","title":"Reinforcement Learning and Life Cycle Assessment for a Circular Economy -- Towards Progressive Computer Science","date":"2025-03-13","arxiv_id":"2503.10822","n_code_links":0,"syntology":null},{"paper":null,"slug":"alignment-agency-and-autonomy-in-frontier-ai","title":"Alignment, Agency and Autonomy in Frontier AI: A Systems Engineering Perspective","date":"2025-02-20","arxiv_id":"2503.05748","n_code_links":0,"syntology":null},{"paper":"/paper/playing-hex-and-counter-wargames-using","slug":"playing-hex-and-counter-wargames-using","title":"Playing Hex and Counter Wargames using Reinforcement Learning and Recurrent Neural Networks","date":"2025-02-19","arxiv_id":"2502.13918","n_code_links":1,"syntology":null},{"paper":"/paper/on-the-emergence-of-thinking-in-llms-i","slug":"on-the-emergence-of-thinking-in-llms-i","title":"On the Emergence of Thinking in LLMs I: Searching for the Right Intuition","date":"2025-02-10","arxiv_id":"2502.06773","n_code_links":4,"syntology":{"ran":11,"of":13,"n_ran_checked":6,"n_instrument":5,"unverified":2,"pointer_only":9,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 2 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","official":{"repos":["GuanghaoYe/Emergence-of-Thinking"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"towards-intrinsic-self-correction-enhancement","title":"Towards Intrinsic Self-Correction Enhancement in Monte Carlo Tree Search Boosted Reasoning via Iterative Preference Learning","date":"2024-12-23","arxiv_id":"2412.17397","n_code_links":0,"syntology":null},{"paper":"/paper/alphazero-neural-scaling-and-zipf-s-law-a","slug":"alphazero-neural-scaling-and-zipf-s-law-a","title":"AlphaZero Neural Scaling and Zipf's Law: a Tale of Board Games and Power Laws","date":"2024-12-16","arxiv_id":"2412.11979","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":4,"n_instrument":2,"unverified":2,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["orenneumann/alphazero_zipfs_law"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mastering-nim-and-impartial-games-with-weak","title":"Mastering NIM and Impartial Games with Weak Neural Networks: An AlphaZero-inspired Multi-Frame Approach","date":"2024-11-10","arxiv_id":"2411.06403","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-chess-reinforcement-learning-with","slug":"enhancing-chess-reinforcement-learning-with","title":"Enhancing Chess Reinforcement Learning with Graph Representation","date":"2024-10-31","arxiv_id":"2410.23753","n_code_links":1,"syntology":null},{"paper":"/paper/bayes-adaptive-monte-carlo-tree-search-for","slug":"bayes-adaptive-monte-carlo-tree-search-for","title":"Bayes Adaptive Monte Carlo Tree Search for Offline Model-based Reinforcement Learning","date":"2024-10-15","arxiv_id":"2410.11234","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lucascjysdl/offline-rl-kit"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"restnet-defense-against-adversarial-policies","title":"ResTNet: Defense against Adversarial Policies via Transformer in Computer Go","date":"2024-10-07","arxiv_id":"2410.05347","n_code_links":0,"syntology":null},{"paper":"/paper/maia-2-a-unified-model-for-human-ai-alignment","slug":"maia-2-a-unified-model-for-human-ai-alignment","title":"Maia-2: A Unified Model for Human-AI Alignment in Chess","date":"2024-09-30","arxiv_id":"2409.20553","n_code_links":2,"syntology":{"ran":8,"of":18,"n_ran_checked":1,"n_instrument":7,"unverified":10,"pointer_only":11,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 7 where Syntology's instrument failed) · 10 unverified","official":{"repos":["csslab/maia2"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/mastering-chess-with-a-transformer-model","slug":"mastering-chess-with-a-transformer-model","title":"Mastering Chess with a Transformer Model","date":"2024-09-18","arxiv_id":"2409.12272","n_code_links":1,"syntology":null},{"paper":"/paper/flexible-game-playing-ai-with-alphavit","slug":"flexible-game-playing-ai-with-alphavit","title":"AlphaViT: A Flexible Game-Playing AI for Multiple Games and Variable Board Sizes","date":"2024-08-25","arxiv_id":"2408.13871","n_code_links":1,"syntology":null},{"paper":null,"slug":"shortcircuit-alphazero-driven-circuit-design","title":"ShortCircuit: AlphaZero-Driven Circuit Design","date":"2024-08-19","arxiv_id":"2408.09858","n_code_links":0,"syntology":null},{"paper":null,"slug":"structure-and-reduction-of-mcts-for","title":"Structure and Reduction of MCTS for Explainable-AI","date":"2024-08-10","arxiv_id":"2408.05488","n_code_links":0,"syntology":null},{"paper":null,"slug":"provably-efficient-long-horizon-exploration","title":"Provably Efficient Long-Horizon Exploration in Monte Carlo Tree Search through State Occupancy Regularization","date":"2024-07-07","arxiv_id":"2407.05511","n_code_links":0,"syntology":null},{"paper":null,"slug":"alphazeroes-direct-score-maximization","title":"AlphaZeroES: Direct score maximization outperforms planning loss minimization","date":"2024-06-12","arxiv_id":"2406.08687","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-play-7-wonders-duel-without-human","title":"Learning to Play 7 Wonders Duel Without Human Supervision","date":"2024-06-02","arxiv_id":"2406.00741","n_code_links":0,"syntology":null},{"paper":null,"slug":"model-predictive-control-and-reinforcement-1","title":"Model Predictive Control and Reinforcement Learning: A Unified Framework Based on Dynamic Programming","date":"2024-06-02","arxiv_id":"2406.00592","n_code_links":0,"syntology":null},{"paper":null,"slug":"super-exponential-regret-for-uct-alphago-and","title":"Super-Exponential Regret for UCT, AlphaGo and Variants","date":"2024-05-07","arxiv_id":"2405.04407","n_code_links":0,"syntology":null},{"paper":null,"slug":"model-based-reinforcement-learning-for-8","title":"Model-based reinforcement learning for protein backbone design","date":"2024-05-03","arxiv_id":"2405.01983","n_code_links":0,"syntology":null},{"paper":"/paper/monte-carlo-tree-search-boosts-reasoning-via","slug":"monte-carlo-tree-search-boosts-reasoning-via","title":"Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning","date":"2024-05-01","arxiv_id":"2405.00451","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["YuxiXie/MCTS-DPO"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/policy-mirror-descent-with-lookahead","slug":"policy-mirror-descent-with-lookahead","title":"Policy Mirror Descent with Lookahead","date":"2024-03-21","arxiv_id":"2403.14156","n_code_links":1,"syntology":null},{"paper":"/paper/smx-sequential-monte-carlo-planning-for","slug":"smx-sequential-monte-carlo-planning-for","title":"SPO: Sequential Monte Carlo Policy Optimisation","date":"2024-02-12","arxiv_id":"2402.07963","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/grandmaster-level-chess-without-search","slug":"grandmaster-level-chess-without-search","title":"Amortized Planning with Large-Scale Transformers: A Case Study on Chess","date":"2024-02-07","arxiv_id":"2402.04494","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":3,"n_instrument":2,"unverified":2,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["google-deepmind/searchless_chess"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mastering-zero-shot-interactions-in","title":"Mastering Zero-Shot Interactions in Cooperative and Competitive Simultaneous Games","date":"2024-02-05","arxiv_id":"2402.03136","n_code_links":0,"syntology":null},{"paper":null,"slug":"discovering-mathematical-formulas-from-data","title":"Discovering Mathematical Formulas from Data via GPT-guided Monte Carlo Tree Search","date":"2024-01-24","arxiv_id":"2401.14424","n_code_links":0,"syntology":null},{"paper":"/paper/decision-making-in-non-stationary-1","slug":"decision-making-in-non-stationary-1","title":"Decision Making in Non-Stationary Environments with Policy-Augmented Search","date":"2024-01-06","arxiv_id":"2401.03197","n_code_links":1,"syntology":null},{"paper":null,"slug":"decentralized-monte-carlo-tree-search-for","title":"Decentralized Monte Carlo Tree Search for Partially Observable Multi-agent Pathfinding","date":"2023-12-26","arxiv_id":"2312.15908","n_code_links":0,"syntology":null},{"paper":null,"slug":"fast-and-knowledge-free-deep-learning-for","title":"Fast and Knowledge-Free Deep Learning for General Game Playing (Student Abstract)","date":"2023-12-21","arxiv_id":"2312.14121","n_code_links":0,"syntology":null},{"paper":null,"slug":"demand-response-for-residential-building","title":"Demand response for residential building heating: Effective Monte Carlo Tree Search control based on physics-informed neural networks","date":"2023-12-06","arxiv_id":"2312.03365","n_code_links":0,"syntology":null},{"paper":"/paper/game-solving-with-online-fine-tuning","slug":"game-solving-with-online-fine-tuning","title":"Game Solving with Online Fine-Tuning","date":"2023-11-13","arxiv_id":"2311.07178","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 5 samples that ran constructed an object rather than computing a result","official":{"repos":["rlglab/online-fine-tuning-solver"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":5,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"finding-increasingly-large-extremal-graphs","title":"Finding Increasingly Large Extremal Graphs with AlphaZero and Tabu Search","date":"2023-11-06","arxiv_id":"2311.03583","n_code_links":0,"syntology":null},{"paper":null,"slug":"bridging-the-human-ai-knowledge-gap-concept","title":"Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero","date":"2023-10-25","arxiv_id":"2310.16410","n_code_links":0,"syntology":null},{"paper":"/paper/minizero-comparative-analysis-of-alphazero","slug":"minizero-comparative-analysis-of-alphazero","title":"MiniZero: Comparative Analysis of AlphaZero and MuZero on Go, Othello, and Atari Games","date":"2023-10-17","arxiv_id":"2310.11305","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["rlglab/minizero"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/expected-flow-networks-in-stochastic","slug":"expected-flow-networks-in-stochastic","title":"Expected flow networks in stochastic environments and two-player zero-sum games","date":"2023-10-04","arxiv_id":"2310.02779","n_code_links":1,"syntology":{"ran":0,"of":4,"n_ran_checked":0,"n_instrument":0,"unverified":4,"pointer_only":4,"phrase":"0 ran · 4 unverified","official":{"repos":["gfnorg/adversarialflownetworks"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"paper":null,"slug":"iterative-option-discovery-for-planning-by","title":"Iterative Option Discovery for Planning, by Planning","date":"2023-10-02","arxiv_id":"2310.01569","n_code_links":0,"syntology":null},{"paper":"/paper/generalized-weighted-path-consistency-for","slug":"generalized-weighted-path-consistency-for","title":"Generalized Weighted Path Consistency for Mastering Atari Games","date":"2023-09-21","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"self-predictive-universal-ai","title":"Self-Predictive Universal AI","date":"2023-09-21","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/information-based-explanation-methods-for","slug":"information-based-explanation-methods-for","title":"Information based explanation methods for deep learning agents -- with applications on large open-source chess models","date":"2023-09-18","arxiv_id":"2309.09702","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["patrik-ha/ii-map"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"chain-of-thought-reasoning-is-a-policy","title":"Chain-of-Thought Reasoning is a Policy Improvement Operator","date":"2023-09-15","arxiv_id":"2309.08589","n_code_links":0,"syntology":null},{"paper":null,"slug":"alphazero-gomoku","title":"AlphaZero Gomoku","date":"2023-09-04","arxiv_id":"2309.01294","n_code_links":0,"syntology":null},{"paper":null,"slug":"concepts-is-all-you-need-a-more-direct-path","title":"Concepts is All You Need: A More Direct Path to AGI","date":"2023-09-04","arxiv_id":"2309.01622","n_code_links":0,"syntology":null},{"paper":null,"slug":"diversifying-ai-towards-creative-chess-with","title":"Diversifying AI: Towards Creative Chess with AlphaZero","date":"2023-08-17","arxiv_id":"2308.09175","n_code_links":0,"syntology":null},{"paper":null,"slug":"matrix-diagonalization-as-a-board-game","title":"Matrix Diagonalization as a Board Game: Teaching an Eigensolver the Fastest Path to Solution","date":"2023-06-16","arxiv_id":"2306.10075","n_code_links":0,"syntology":null},{"paper":"/paper/policy-based-self-competition-for-planning","slug":"policy-based-self-competition-for-planning","title":"Policy-Based Self-Competition for Planning Problems","date":"2023-06-07","arxiv_id":"2306.04403","n_code_links":1,"syntology":null},{"paper":null,"slug":"representation-matters-the-game-of-chess","title":"Representation Matters for Mastering Chess: Improved Feature Representation in AlphaZero Outperforms Switching to Transformers","date":"2023-04-28","arxiv_id":"2304.14918","n_code_links":0,"syntology":null},{"paper":"/paper/pgx-hardware-accelerated-parallel-game-1","slug":"pgx-hardware-accelerated-parallel-game-1","title":"Pgx: Hardware-Accelerated Parallel Game Simulators for Reinforcement Learning","date":"2023-03-29","arxiv_id":"2303.17503","n_code_links":1,"syntology":{"ran":0,"of":3,"n_ran_checked":0,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"0 ran · 3 unverified","official":{"repos":["sotetsuk/pgx"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"paper":"/paper/targeted-search-control-in-alphazero-for","slug":"targeted-search-control-in-alphazero-for","title":"Targeted Search Control in AlphaZero for Effective Policy Improvement","date":"2023-02-23","arxiv_id":"2302.12359","n_code_links":1,"syntology":null},{"paper":null,"slug":"policy-value-alignment-and-robustness-in","title":"Policy-Value Alignment and Robustness in Search-based Multi-Agent Learning","date":"2023-01-27","arxiv_id":"2301.11857","n_code_links":0,"syntology":null},{"paper":"/paper/evaluation-beyond-task-performance-analyzing","slug":"evaluation-beyond-task-performance-analyzing","title":"Evaluation Beyond Task Performance: Analyzing Concepts in AlphaZero in Hex","date":"2022-11-26","arxiv_id":"2211.14673","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":2,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jzf2101/alphatology"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"alphasnake-policy-iteration-on-a","title":"AlphaSnake: Policy Iteration on a Nondeterministic NP-hard Markov Decision Process","date":"2022-11-17","arxiv_id":"2211.09622","n_code_links":0,"syntology":null},{"paper":"/paper/are-alphazero-like-agents-robust-to","slug":"are-alphazero-like-agents-robust-to","title":"Are AlphaZero-like Agents Robust to Adversarial Perturbations?","date":"2022-11-07","arxiv_id":"2211.03769","n_code_links":1,"syntology":null},{"paper":"/paper/scaling-laws-for-a-multi-agent-reinforcement","slug":"scaling-laws-for-a-multi-agent-reinforcement","title":"Scaling Laws for a Multi-Agent Reinforcement Learning Model","date":"2022-09-29","arxiv_id":"2210.00849","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["orenneumann/alphazero-scaling-laws"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/neural-networks-for-chess","slug":"neural-networks-for-chess","title":"Neural Networks for Chess","date":"2022-09-03","arxiv_id":"2209.01506","n_code_links":2,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["asdfjkl/neural_network_chess"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/brick-tic-tac-toe-exploring-the","slug":"brick-tic-tac-toe-exploring-the","title":"Brick Tic-Tac-Toe: Exploring the Generalizability of AlphaZero to Novel Test Environments","date":"2022-07-13","arxiv_id":"2207.05991","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-alphazero-inspired-approach-to-solving","title":"An AlphaZero-Inspired Approach to Solving Search Problems","date":"2022-07-02","arxiv_id":"2207.00919","n_code_links":0,"syntology":null},{"paper":null,"slug":"policy-gradient-algorithms-with-monte-carlo","title":"Policy Gradient Algorithms with Monte Carlo Tree Learning for Non-Markov Decision Processes","date":"2022-06-02","arxiv_id":"2206.01011","n_code_links":0,"syntology":null},{"paper":"/paper/impartial-games-a-challenge-for-reinforcement","slug":"impartial-games-a-challenge-for-reinforcement","title":"Impartial Games: A Challenge for Reinforcement Learning","date":"2022-05-25","arxiv_id":"2205.12787","n_code_links":1,"syntology":null},{"paper":"/paper/hypertree-proof-search-for-neural-theorem","slug":"hypertree-proof-search-for-neural-theorem","title":"HyperTree Proof Search for Neural Theorem Proving","date":"2022-05-23","arxiv_id":"2205.11491","n_code_links":0,"syntology":null},{"paper":"/paper/alphazero-inspired-general-board-game","slug":"alphazero-inspired-general-board-game","title":"AlphaZero-Inspired Game Learning: Faster Training by Using MCTS Only at Test Time","date":"2022-04-28","arxiv_id":"2204.13307","n_code_links":1,"syntology":null},{"paper":null,"slug":"leela-zero-score-a-study-of-a-score-based","title":"Score vs. Winrate in Score-Based Games: which Reward for Reinforcement Learning?","date":"2022-01-31","arxiv_id":"2201.13176","n_code_links":0,"syntology":null},{"paper":"/paper/a-novel-approach-to-solving-goal-achieving","slug":"a-novel-approach-to-solving-goal-achieving","title":"A Novel Approach to Solving Goal-Achieving Problems for Board Games","date":"2021-12-05","arxiv_id":"2112.02563","n_code_links":1,"syntology":null},{"paper":null,"slug":"acquisition-of-chess-knowledge-in-alphazero","title":"Acquisition of Chess Knowledge in AlphaZero","date":"2021-11-17","arxiv_id":"2111.09259","n_code_links":0,"syntology":null},{"paper":"/paper/alphadda-game-artificial-intelligence-with","slug":"alphadda-game-artificial-intelligence-with","title":"AlphaDDA: Strategies for Adjusting the Playing Strength of a Fully Trained AlphaZero System to a Suitable Human Training Partner","date":"2021-11-11","arxiv_id":"2111.06266","n_code_links":1,"syntology":null},{"paper":"/paper/alphazero-based-proof-cost-network-to-aid","slug":"alphazero-based-proof-cost-network-to-aid","title":"AlphaZero-based Proof Cost Network to Aid Game Solving","date":"2021-09-29","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"goal-directed-planning-via-hindsight","title":"Goal-Directed Planning via Hindsight Experience Replay","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/policy-improvement-by-planning-with-gumbel","slug":"policy-improvement-by-planning-with-gumbel","title":"Policy improvement by planning with Gumbel","date":"2021-09-29","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":null,"slug":"train-on-small-play-the-large-scaling-up","title":"Train on Small, Play the Large: Scaling Up Board Games with AlphaZero and GNN","date":"2021-07-18","arxiv_id":"2107.08387","n_code_links":0,"syntology":null},{"paper":"/paper/scaling-scaling-laws-with-board-games","slug":"scaling-scaling-laws-with-board-games","title":"Scaling Scaling Laws with Board Games","date":"2021-04-07","arxiv_id":"2104.03113","n_code_links":2,"syntology":{"ran":13,"of":20,"n_ran_checked":13,"n_instrument":0,"unverified":7,"pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","official":null}},{"paper":null,"slug":"dual-monte-carlo-tree-search","title":"Dual Monte Carlo Tree Search","date":"2021-03-21","arxiv_id":"2103.11517","n_code_links":0,"syntology":null},{"paper":null,"slug":"combining-off-and-on-policy-training-in-model","title":"Combining Off and On-Policy Training in Model-Based Reinforcement Learning","date":"2021-02-24","arxiv_id":"2102.12194","n_code_links":0,"syntology":null},{"paper":"/paper/mastering-terra-mystica-applying-self-play-to","slug":"mastering-terra-mystica-applying-self-play-to","title":"Mastering Terra Mystica: Applying Self-Play to Multi-agent Cooperative Board Games","date":"2021-02-21","arxiv_id":"2102.10540","n_code_links":1,"syntology":null},{"paper":"/paper/robust-and-efficient-planning-using-adaptive","slug":"robust-and-efficient-planning-using-adaptive","title":"Planning and Learning Using Adaptive Entropy Tree Search","date":"2021-02-12","arxiv_id":"2102.06808","n_code_links":1,"syntology":null},{"paper":null,"slug":"solving-qsat-problems-with-neural-mcts","title":"Solving QSAT problems with neural MCTS","date":"2021-01-17","arxiv_id":"2101.06619","n_code_links":0,"syntology":null},{"paper":null,"slug":"first-order-problem-solving-through-neural","title":"First-Order Problem Solving through Neural MCTS based Reinforcement Learning","date":"2021-01-11","arxiv_id":"2101.04167","n_code_links":0,"syntology":null},{"paper":null,"slug":"domain-knowledge-in-exploration-noise-in","title":"Domain Knowledge in Exploration Noise in AlphaZero","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"playing-nondeterministic-games-through","title":"Playing Nondeterministic Games through Planning with a Learned Model","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/monte-carlo-graph-search-for-alphazero","slug":"monte-carlo-graph-search-for-alphazero","title":"Monte-Carlo Graph Search for AlphaZero","date":"2020-12-20","arxiv_id":"2012.11045","n_code_links":3,"syntology":null},{"paper":null,"slug":"learning-to-stop-dynamic-simulation-monte","title":"Learning to Stop: Dynamic Simulation Monte-Carlo Tree Search","date":"2020-12-14","arxiv_id":"2012.07910","n_code_links":0,"syntology":null},{"paper":"/paper/assessing-game-balance-with-alphazero","slug":"assessing-game-balance-with-alphazero","title":"Assessing Game Balance with AlphaZero: Exploring Alternative Rule Sets in Chess","date":"2020-09-09","arxiv_id":"2009.04374","n_code_links":2,"syntology":null},{"paper":"/paper/learning-personalized-models-of-human","slug":"learning-personalized-models-of-human","title":"Learning Models of Individual Behavior in Chess","date":"2020-08-23","arxiv_id":"2008.10086","n_code_links":1,"syntology":null},{"paper":"/paper/combining-deep-reinforcement-learning-and-1","slug":"combining-deep-reinforcement-learning-and-1","title":"Combining Deep Reinforcement Learning and Search for Imperfect-Information Games","date":"2020-07-27","arxiv_id":"2007.13544","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["facebookresearch/rebel"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"learning-compositional-neural-programs-for","title":"Learning Compositional Neural Programs for Continuous Control","date":"2020-07-27","arxiv_id":"2007.13363","n_code_links":0,"syntology":null},{"paper":"/paper/monte-carlo-tree-search-as-regularized-policy","slug":"monte-carlo-tree-search-as-regularized-policy","title":"Monte-Carlo Tree Search as Regularized Policy Optimization","date":"2020-07-24","arxiv_id":"2007.12509","n_code_links":3,"syntology":null},{"paper":null,"slug":"convex-regularization-in-monte-carlo-tree","title":"Convex Regularization in Monte-Carlo Tree Search","date":"2020-07-01","arxiv_id":"2007.00391","n_code_links":0,"syntology":null},{"paper":"/paper/aligning-superhuman-ai-and-human-behavior","slug":"aligning-superhuman-ai-and-human-behavior","title":"Aligning Superhuman AI with Human Behavior: Chess as a Model System","date":"2020-06-02","arxiv_id":"2006.01855","n_code_links":1,"syntology":null},{"paper":"/paper/think-too-fast-nor-too-slow-the-computational","slug":"think-too-fast-nor-too-slow-the-computational","title":"Think Too Fast Nor Too Slow: The Computational Trade-off Between Planning And Reinforcement Learning","date":"2020-05-15","arxiv_id":"2005.07404","n_code_links":1,"syntology":null},{"paper":"/paper/neural-machine-translation-with-monte-carlo","slug":"neural-machine-translation-with-monte-carlo","title":"Neural Machine Translation with Monte-Carlo Tree Search","date":"2020-04-27","arxiv_id":"2004.12527","n_code_links":1,"syntology":null},{"paper":null,"slug":"warm-start-alphazero-self-play-search","title":"Warm-Start AlphaZero Self-Play Search Enhancements","date":"2020-04-26","arxiv_id":"2004.12357","n_code_links":0,"syntology":null},{"paper":null,"slug":"approximate-exploitability-learning-a-best","title":"Approximate exploitability: Learning a best response in large games","date":"2020-04-20","arxiv_id":"2004.09677","n_code_links":0,"syntology":null},{"paper":"/paper/accelerating-and-improving-alphazero-using","slug":"accelerating-and-improving-alphazero-using","title":"Accelerating and Improving AlphaZero Using Population Based Training","date":"2020-03-13","arxiv_id":"2003.06212","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-to-resolve-alliance-dilemmas-in-many","title":"Learning to Resolve Alliance Dilemmas in Many-Player Zero-Sum Games","date":"2020-02-27","arxiv_id":"2003.00799","n_code_links":0,"syntology":null},{"paper":null,"slug":"polygames-improved-zero-learning","title":"Polygames: Improved Zero Learning","date":"2020-01-27","arxiv_id":"2001.09832","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-play-learning-without-a-reward-metric","title":"Self-Play Learning Without a Reward Metric","date":"2019-12-16","arxiv_id":"1912.07557","n_code_links":0,"syntology":null},{"paper":"/paper/mastering-atari-go-chess-and-shogi-by","slug":"mastering-atari-go-chess-and-shogi-by","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","date":"2019-11-19","arxiv_id":"1911.08265","n_code_links":18,"syntology":{"ran":43,"of":64,"n_ran_checked":43,"n_instrument":0,"unverified":21,"pointer_only":62,"phrase":"43 ran (of which 36 constructed an object rather than computing a result; 43 with no instrument failure: 4 honoured, 0 violated, 39 with no contract checked; 0 where Syntology's instrument failed) · 21 unverified","official":null}},{"paper":"/paper/multiplayer-alphazero","slug":"multiplayer-alphazero","title":"Multiplayer AlphaZero","date":"2019-10-29","arxiv_id":"1910.13012","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-the-performance-of-deep-residual","title":"Exploring the Performance of Deep Residual Networks in Crazyhouse Chess","date":"2019-08-25","arxiv_id":"1908.09296","n_code_links":0,"syntology":null}],"papers_shown":100,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":114,"with_a_code_link":60,"where_syntology_ran_a_sample":17,"not_listed_spam_title":0,"listed":114,"listed_where_code_ran":17,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":16,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":16,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":17,"papers_where_code_ran_first_page":"/method/alphazero/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"archive","page":2,"of":2,"url":"/method/alphazero/papers/2","json":"/method/alphazero/papers/2.json","rows":14},{"order":"ran","page":1,"of":1,"url":"/method/alphazero/papers/ran/1","json":"/method/alphazero/papers/ran/1.json","rows":17}],"tasks":[{"task":"/task/board-games","name":"Board Games","papers":26},{"task":"/task/reinforcement-learning-1","name":"Reinforcement Learning (RL)","papers":26},{"task":"/task/reinforcement-learning-2","name":"reinforcement-learning","papers":22},{"task":"/task/reinforcement-learning","name":"Reinforcement Learning","papers":20},{"task":"/task/decision-making","name":"Decision Making","papers":15},{"task":"/task/atari-games","name":"Atari Games","papers":8},{"task":"/task/deep-reinforcement-learning","name":"Deep Reinforcement Learning","papers":8},{"task":"/task/game-of-go","name":"Game of Go","papers":8},{"task":"/task/game-of-chess","name":"Game of Chess","papers":6},{"task":"/task/sequential-decision-making","name":"Sequential Decision Making","papers":5},{"task":null,"name":"GPU","papers":4},{"task":"/task/model-based-reinforcement-learning","name":"Model-based Reinforcement Learning","papers":4},{"task":"/task/math","name":"Math","papers":3},{"task":"/task/q-learning","name":"Q-Learning","papers":3},{"task":null,"name":"CPU","papers":2},{"task":"/task/combinatorial-optimization","name":"Combinatorial Optimization","papers":2},{"task":"/task/gsm8k","name":"GSM8K","papers":2},{"task":"/task/game-of-shogi","name":"Game of Shogi","papers":2},{"task":"/task/graph-neural-network","name":"Graph Neural Network","papers":2},{"task":"/task/model-predictive-control","name":"Model Predictive Control","papers":2}],"tasks_shown":20,"n_tasks":65,"usage_by_year":[{"year":"2017","papers":1},{"year":"2018","papers":4},{"year":"2019","papers":13},{"year":"2020","papers":16},{"year":"2021","papers":16},{"year":"2022","papers":12},{"year":"2023","papers":22},{"year":"2024","papers":24},{"year":"2025","papers":6}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/alphazero"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=AlphaZero","read_at":"2026-10-05T00:51:54+00:00","query":"AlphaZero","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":"1712.01815","repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'AlphaZero' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["a variant of AlphaZero","AlphaZero Auxiliary Loss (AZAL)","Stochastic Gumbel AlphaZero (SGAZ)","RL framework inspired by AlphaZero and AlphaProof"],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"eaa6fd076913c48edbb801c90f3405542f9c389a84e5ea07c9eb6322f6ad559f","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}