{"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/a2c","slug":"a2c","name":"A2C","full_name":"A2C","full_name_withheld":false,"description_markdown":"**A2C**, or **Advantage Actor Critic**, is a synchronous version of the [A3C](https://paperswithcode.com/method/a3c) policy gradient method. As an alternative to the asynchronous implementation of A3C, A2C is a synchronous, deterministic implementation that waits for each actor to finish its segment of experience before updating, averaging over all of the actors. This more effectively uses GPUs due to larger batch sizes.\r\n\r\nImage Credit: [OpenAI Baselines](https://openai.com/blog/baselines-acktr-a2c/)","description_state":"present","introduced_year":null,"introduced_by":{"title":"Asynchronous Methods for Deep Reinforcement Learning","paper":"/paper/asynchronous-methods-for-deep-reinforcement","first_author":"Volodymyr Mnih","n_authors":8,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/asynchronous-methods-for-deep-reinforcement"},"source":{"url":"http://arxiv.org/abs/1602.01783v2","title":"Asynchronous Methods for Deep Reinforcement Learning","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":"Policy Gradient Methods","url":"/methods/category/policy-gradient-methods","pwc_aliases":[]}],"n_papers_tagged":82,"archive_num_papers":82,"papers_newest_first":[{"paper":null,"slug":"monte-carlo-beam-search-for-actor-critic","title":"Monte Carlo Beam Search for Actor-Critic Reinforcement Learning in Continuous Control","date":"2025-05-13","arxiv_id":"2505.09029","n_code_links":0,"syntology":null},{"paper":null,"slug":"ensemble-rl-through-classifier-models","title":"Ensemble RL through Classifier Models: Enhancing Risk-Return Trade-offs in Trading Strategies","date":"2025-02-23","arxiv_id":"2502.17518","n_code_links":0,"syntology":null},{"paper":null,"slug":"continuous-learning-conversational-ai-a","title":"Continuous Learning Conversational AI: A Personalized Agent Framework via A2C Reinforcement Learning","date":"2025-02-18","arxiv_id":"2502.12876","n_code_links":0,"syntology":null},{"paper":"/paper/evorl-a-gpu-accelerated-framework-for","slug":"evorl-a-gpu-accelerated-framework-for","title":"EvoRL: A GPU-accelerated Framework for Evolutionary Reinforcement Learning","date":"2025-01-25","arxiv_id":"2501.15129","n_code_links":2,"syntology":null},{"paper":null,"slug":"rationality-based-innate-values-driven","title":"Innate-Values-driven Reinforcement Learning based Cognitive Modeling","date":"2024-11-14","arxiv_id":"2411.09160","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-reinforcement-learning-strategies-in","title":"Deep Reinforcement Learning Strategies in Finance: Insights into Asset Holding, Trading Behavior, and Purchase Diversity","date":"2024-06-29","arxiv_id":"2407.09557","n_code_links":0,"syntology":null},{"paper":null,"slug":"multistep-criticality-search-and-power","title":"Multistep Criticality Search and Power Shaping in Microreactors with Reinforcement Learning","date":"2024-06-22","arxiv_id":"2406.15931","n_code_links":0,"syntology":null},{"paper":null,"slug":"biological-neurons-compete-with-deep","title":"Biological Neurons Compete with Deep Reinforcement Learning in Sample Efficiency in a Simulated Gameworld","date":"2024-05-27","arxiv_id":"2405.16946","n_code_links":0,"syntology":null},{"paper":"/paper/symmetric-reinforcement-learning-loss-for","slug":"symmetric-reinforcement-learning-loss-for","title":"Symmetric Reinforcement Learning Loss for Robust Learning on Diverse Tasks and Model Scales","date":"2024-05-27","arxiv_id":"2405.17618","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-reinforcement-learning-via-large","title":"Extracting Heuristics from Large Language Models for Reward Shaping in Reinforcement Learning","date":"2024-05-24","arxiv_id":"2405.15194","n_code_links":0,"syntology":null},{"paper":null,"slug":"portfolio-management-using-deep-reinforcement","title":"Portfolio Management using Deep Reinforcement Learning","date":"2024-05-01","arxiv_id":"2405.01604","n_code_links":0,"syntology":null},{"paper":"/paper/breaching-the-bottleneck-evolutionary","slug":"breaching-the-bottleneck-evolutionary","title":"Breaching the Bottleneck: Evolutionary Transition from Reward-Driven Learning to Reward-Agnostic Domain-Adapted Learning in Neuromodulated Neural Nets","date":"2024-04-19","arxiv_id":"2404.12631","n_code_links":1,"syntology":null},{"paper":null,"slug":"a2c-a-modular-multi-stage-collaborative","title":"A2C: A Modular Multi-stage Collaborative Decision Framework for Human-AI Teams","date":"2024-01-25","arxiv_id":"2401.14432","n_code_links":0,"syntology":null},{"paper":null,"slug":"epidemic-decision-making-system-based","title":"Epidemic Decision-making System Based Federated Reinforcement Learning","date":"2023-11-03","arxiv_id":"2311.01749","n_code_links":0,"syntology":null},{"paper":null,"slug":"diagnosis-oriented-medical-image-compression","title":"Diagnosis-oriented Medical Image Compression with Efficient Transfer Learning","date":"2023-10-20","arxiv_id":"2310.13250","n_code_links":0,"syntology":null},{"paper":"/paper/deep-reinforcement-learning-based-intelligent-2","slug":"deep-reinforcement-learning-based-intelligent-2","title":"Deep Reinforcement Learning-based Intelligent Traffic Signal Controls with Optimized CO2 emissions","date":"2023-10-19","arxiv_id":"2310.13129","n_code_links":1,"syntology":null},{"paper":null,"slug":"solving-the-quadratic-assignment-problem","title":"Solving the Quadratic Assignment Problem using Deep Reinforcement Learning","date":"2023-10-02","arxiv_id":"2310.01604","n_code_links":0,"syntology":null},{"paper":null,"slug":"raiju-reinforcement-learning-guided-post","title":"Raijū: Reinforcement Learning-Guided Post-Exploitation for Automating Security Assessment of Network Systems","date":"2023-09-27","arxiv_id":"2309.15518","n_code_links":0,"syntology":null},{"paper":null,"slug":"saf-net-self-attention-fusion-network-for","title":"SAF-Net: Self-Attention Fusion Network for Myocardial Infarction Detection using Multi-View Echocardiography","date":"2023-09-27","arxiv_id":"2309.15520","n_code_links":0,"syntology":null},{"paper":null,"slug":"career-path-recommendations-for-long-term","title":"Career Path Recommendations for Long-term Income Maximization: A Reinforcement Learning Approach","date":"2023-09-11","arxiv_id":"2309.05391","n_code_links":0,"syntology":null},{"paper":null,"slug":"semantic-consistency-for-assuring-reliability","title":"Semantic Consistency for Assuring Reliability of Large Language Models","date":"2023-08-17","arxiv_id":"2308.09138","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-reinforcement-learning-for-esg-financial","title":"Deep Reinforcement Learning for ESG financial portfolio management","date":"2023-06-19","arxiv_id":"2307.09631","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-agent-reinforcement-learning-for-17","title":"Multi-Agent Reinforcement Learning for Network Routing in Integrated Access Backhaul Networks","date":"2023-05-12","arxiv_id":"2305.16170","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-reinforcement-learning-applied-to-an","title":"Deep reinforcement learning applied to an assembly sequence planning problem with user preferences","date":"2023-04-13","arxiv_id":"2304.06567","n_code_links":0,"syntology":null},{"paper":null,"slug":"read-and-reap-the-rewards-learning-to-play","title":"Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals","date":"2023-02-09","arxiv_id":"2302.04449","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-scale-independent-multi-objective","title":"A Scale-Independent Multi-Objective Reinforcement Learning with Convergence Analysis","date":"2023-02-08","arxiv_id":"2302.04179","n_code_links":0,"syntology":null},{"paper":"/paper/learning-fast-and-slow-a-goal-directed-memory","slug":"learning-fast-and-slow-a-goal-directed-memory","title":"Learning, Fast and Slow: A Goal-Directed Memory-Based Approach for Dynamic Environments","date":"2023-01-31","arxiv_id":"2301.13758","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-automating-codenames-spymasters-with","title":"Towards automating Codenames spymasters with deep reinforcement learning","date":"2022-12-28","arxiv_id":"2212.14104","n_code_links":0,"syntology":null},{"paper":"/paper/solving-the-side-chain-packing-arrangement-of","slug":"solving-the-side-chain-packing-arrangement-of","title":"Reinforcement Learning for Molecular Dynamics Optimization: A Stochastic Pontryagin Maximum Principle Approach","date":"2022-12-06","arxiv_id":"2212.03320","n_code_links":1,"syntology":null},{"paper":null,"slug":"anticipatory-fleet-repositioning-for-shared","title":"Towards More Efficient Shared Autonomous Mobility: A Learning-Based Fleet Repositioning Approach","date":"2022-10-16","arxiv_id":"2210.08659","n_code_links":0,"syntology":null},{"paper":null,"slug":"reinforcement-learning-for-cognitive-delay","title":"Reinforcement Learning for Cognitive Delay/Disruption Tolerant Network Node Management in an LEO-based Satellite Constellation","date":"2022-09-27","arxiv_id":"2209.13237","n_code_links":0,"syntology":null},{"paper":null,"slug":"variance-reduction-for-policy-gradient","title":"Variance Reduction for Policy-Gradient Methods via Empirical Variance Minimization","date":"2022-06-14","arxiv_id":"2206.06827","n_code_links":0,"syntology":null},{"paper":"/paper/a2c-is-a-special-case-of-ppo","slug":"a2c-is-a-special-case-of-ppo","title":"A2C is a special case of PPO","date":"2022-05-18","arxiv_id":"2205.09123","n_code_links":1,"syntology":null},{"paper":"/paper/cliff-diving-exploring-reward-surfaces-in","slug":"cliff-diving-exploring-reward-surfaces-in","title":"Cliff Diving: Exploring Reward Surfaces in Reinforcement Learning Environments","date":"2022-05-14","arxiv_id":"2205.07015","n_code_links":0,"syntology":{"ran":2,"of":4,"n_ran_checked":1,"n_instrument":1,"unverified":2,"pointer_only":1,"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) · 2 unverified","official":null}},{"paper":null,"slug":"consistent-dropout-for-policy-gradient","title":"Consistent Dropout for Policy Gradient Reinforcement Learning","date":"2022-02-23","arxiv_id":"2202.11818","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-awareness-safety-of-deep-reinforcement","title":"Self-Awareness Safety of Deep Reinforcement Learning in Road Traffic Junction Driving","date":"2022-01-20","arxiv_id":"2201.08116","n_code_links":0,"syntology":null},{"paper":null,"slug":"recursive-least-squares-advantage-actor","title":"Recursive Least Squares Advantage Actor-Critic Algorithms","date":"2022-01-15","arxiv_id":"2201.05918","n_code_links":0,"syntology":null},{"paper":"/paper/early-myocardial-infarction-detection-over","slug":"early-myocardial-infarction-detection-over","title":"Early Myocardial Infarction Detection over Multi-view Echocardiography","date":"2021-11-09","arxiv_id":"2111.05790","n_code_links":1,"syntology":null},{"paper":null,"slug":"structure-aware-reinforcement-learning-for","title":"Structure-aware reinforcement learning for node-overload protection in mobile edge computing","date":"2021-06-29","arxiv_id":"2107.01025","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-plan-via-a-multi-step-policy","title":"Learning to Plan via a Multi-Step Policy Regression Method","date":"2021-06-18","arxiv_id":"2106.10075","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-practical-credit-assignment-for-deep","title":"Towards Practical Credit Assignment for Deep Reinforcement Learning","date":"2021-06-08","arxiv_id":"2106.04499","n_code_links":0,"syntology":null},{"paper":"/paper/deep-reinforcement-learning-for-adaptive-3","slug":"deep-reinforcement-learning-for-adaptive-3","title":"Deep Reinforcement Learning for Adaptive Exploration of Unknown Environments","date":"2021-05-04","arxiv_id":"2105.01606","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-survey-of-motion-planning-algorithms-for","title":"A review of motion planning algorithms for intelligent robotics","date":"2021-02-04","arxiv_id":"2102.02376","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-coherent-exploration-for-continuous","title":"Deep Coherent Exploration For Continuous Control","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-information-bottleneck-in","title":"Optimizing Information Bottleneck in Reinforcement Learning: A Stein Variational Approach","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/augmenting-policy-learning-with-routines","slug":"augmenting-policy-learning-with-routines","title":"Augmenting Policy Learning with Routines Discovered from a Single Demonstration","date":"2020-12-23","arxiv_id":"2012.12469","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sjtuytc/-AAAI21-RoutineAugmentedPolicyLearning-RAPL-","sjtuytc/AAAI21-RoutineAugmentedPolicyLearning"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/finrl-a-deep-reinforcement-learning-library","slug":"finrl-a-deep-reinforcement-learning-library","title":"FinRL: A Deep Reinforcement Learning Library for Automated Stock Trading in Quantitative Finance","date":"2020-11-19","arxiv_id":"2011.09607","n_code_links":6,"syntology":null},{"paper":"/paper/tonic-a-deep-reinforcement-learning-library","slug":"tonic-a-deep-reinforcement-learning-library","title":"Tonic: A Deep Reinforcement Learning Library for Fast Prototyping and Benchmarking","date":"2020-11-15","arxiv_id":"2011.07537","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":0,"n_instrument":3,"unverified":1,"pointer_only":0,"phrase":"3 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; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["fabiopardo/tonic"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"the-greatest-teacher-failure-is-using","title":"The Greatest Teacher, Failure is: Using Reinforcement Learning for SFC Placement Based on Availability and Energy Consumption","date":"2020-10-12","arxiv_id":"2010.05711","n_code_links":0,"syntology":null},{"paper":"/paper/value-decomposition-multi-agent-actor-critics","slug":"value-decomposition-multi-agent-actor-critics","title":"Value-Decomposition Multi-Agent Actor-Critics","date":"2020-07-24","arxiv_id":"2007.12306","n_code_links":1,"syntology":null},{"paper":"/paper/generalized-state-dependent-exploration-for","slug":"generalized-state-dependent-exploration-for","title":"Smooth Exploration for Robotic Reinforcement Learning","date":"2020-05-12","arxiv_id":"2005.05719","n_code_links":4,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["DLR-RM/stable-baselines3"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"work-in-progress-temporally-extended","title":"Work in Progress: Temporally Extended Auxiliary Tasks","date":"2020-04-01","arxiv_id":"2004.00600","n_code_links":0,"syntology":null},{"paper":"/paper/particle-based-adaptive-discretization-for","slug":"particle-based-adaptive-discretization-for","title":"PFPN: Continuous Control of Physically Simulated Characters using Particle Filtering Policy Network","date":"2020-03-16","arxiv_id":"2003.06959","n_code_links":1,"syntology":null},{"paper":"/paper/accessing-higher-level-representations-in","slug":"accessing-higher-level-representations-in","title":"Addressing Some Limitations of Transformers with Feedback Memory","date":"2020-02-21","arxiv_id":"2002.09402","n_code_links":4,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["facebookresearch/transformer-sequential"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"paper":null,"slug":"learning-representations-in-reinforcement-1","title":"Learning Representations in Reinforcement Learning: an Information Bottleneck Approach","date":"2020-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/slm-lab-a-comprehensive-benchmark-and-modular-1","slug":"slm-lab-a-comprehensive-benchmark-and-modular-1","title":"SLM Lab: A Comprehensive Benchmark and Modular Software Framework for Reproducible Deep Reinforcement Learning","date":"2019-12-28","arxiv_id":"1912.12482","n_code_links":1,"syntology":{"ran":10,"of":13,"n_ran_checked":10,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["kengz/SLM-Lab"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"buffer-aware-wireless-scheduling-based-on","title":"Buffer-aware Wireless Scheduling based on Deep Reinforcement Learning","date":"2019-11-13","arxiv_id":"1911.05281","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-representations-in-reinforcement","title":"Learning Representations in Reinforcement Learning:An Information Bottleneck Approach","date":"2019-11-12","arxiv_id":"1911.05695","n_code_links":0,"syntology":null},{"paper":null,"slug":"ai-assisted-annotator-using-reinforcement","title":"AI Assisted Annotator using Reinforcement Learning","date":"2019-10-02","arxiv_id":"1910.02052","n_code_links":0,"syntology":null},{"paper":"/paper/quantized-reinforcement-learning-quarl","slug":"quantized-reinforcement-learning-quarl","title":"QuaRL: Quantization for Fast and Environmentally Sustainable Reinforcement Learning","date":"2019-10-02","arxiv_id":"1910.01055","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["harvard-edge/quarl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"190909993","title":"Improving OOV Detection and Resolution with External Language Models in Acoustic-to-Word ASR","date":"2019-09-22","arxiv_id":"1909.09993","n_code_links":0,"syntology":null},{"paper":"/paper/190909902","slug":"190909902","title":"Deep Reinforcement Learning with Modulated Hebbian plus Q Network Architecture","date":"2019-09-21","arxiv_id":"1909.09902","n_code_links":1,"syntology":null},{"paper":"/paper/vision-based-navigation-using-deep","slug":"vision-based-navigation-using-deep","title":"Vision-based Navigation Using Deep Reinforcement Learning","date":"2019-08-08","arxiv_id":"1908.03627","n_code_links":1,"syntology":null},{"paper":null,"slug":"variance-reduction-in-actor-critic-methods","title":"Variance Reduction in Actor Critic Methods (ACM)","date":"2019-07-23","arxiv_id":"1907.09765","n_code_links":0,"syntology":null},{"paper":"/paper/gossip-based-actor-learner-architectures-for","slug":"gossip-based-actor-learner-architectures-for","title":"Gossip-based Actor-Learner Architectures for Deep Reinforcement Learning","date":"2019-06-09","arxiv_id":"1906.04585","n_code_links":1,"syntology":null},{"paper":null,"slug":"rl-based-method-for-benchmarking-the","title":"RL-Based Method for Benchmarking the Adversarial Resilience and Robustness of Deep Reinforcement Learning Policies","date":"2019-06-03","arxiv_id":"1906.01110","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-q-learning-with-q-matrix-transfer","title":"Deep Q-Learning with Q-Matrix Transfer Learning for Novel Fire Evacuation Environment","date":"2019-05-23","arxiv_id":"1905.09673","n_code_links":0,"syntology":null},{"paper":null,"slug":"autonomous-air-traffic-controller-a-deep","title":"Autonomous Air Traffic Controller: A Deep Multi-Agent Reinforcement Learning Approach","date":"2019-05-02","arxiv_id":"1905.01303","n_code_links":0,"syntology":null},{"paper":"/paper/multi-agent-deep-reinforcement-learning-for-2","slug":"multi-agent-deep-reinforcement-learning-for-2","title":"Multi-Agent Deep Reinforcement Learning for Large-scale Traffic Signal Control","date":"2019-03-11","arxiv_id":"1903.04527","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":6,"n_instrument":1,"unverified":2,"pointer_only":1,"phrase":"7 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; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["cts198859/deeprl_signal_control"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"integrating-reinforcement-learning-to-self","title":"Integrating Reinforcement Learning to Self Training for Pulmonary Nodule Segmentation in Chest X-rays","date":"2018-11-21","arxiv_id":"1811.08840","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-initial-attempt-of-combining-visual","title":"An initial attempt of combining visual selective attention with deep reinforcement learning","date":"2018-11-11","arxiv_id":"1811.04407","n_code_links":0,"syntology":null},{"paper":"/paper/representation-learning-with-contrastive","slug":"representation-learning-with-contrastive","title":"Representation Learning with Contrastive Predictive Coding","date":"2018-07-10","arxiv_id":"1807.03748","n_code_links":28,"syntology":{"ran":35,"of":45,"n_ran_checked":30,"n_instrument":5,"unverified":10,"pointer_only":22,"phrase":"35 ran (of which 21 constructed an object rather than computing a result; 30 with no instrument failure: 1 honoured, 0 violated, 29 with no contract checked; 5 where Syntology's instrument failed) · 10 unverified","official":null}},{"paper":"/paper/an-intriguing-failing-of-convolutional-neural","slug":"an-intriguing-failing-of-convolutional-neural","title":"An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution","date":"2018-07-09","arxiv_id":"1807.03247","n_code_links":24,"syntology":{"ran":5,"of":5,"n_ran_checked":3,"n_instrument":2,"unverified":0,"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) · 0 unverified","official":{"repos":["uber-research/coordconv"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"improving-width-based-planning-with-compact","title":"Improving width-based planning with compact policies","date":"2018-06-15","arxiv_id":"1806.05898","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-curiosity-search-intra-life-exploration","title":"Deep Curiosity Search: Intra-Life Exploration Can Improve Performance on Challenging Deep Reinforcement Learning Problems","date":"2018-06-01","arxiv_id":"1806.00553","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-empirical-analysis-of-proximal-policy","title":"An Empirical Analysis of Proximal Policy Optimization with Kronecker-factored Natural Gradients","date":"2018-01-17","arxiv_id":"1801.05566","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-deep-recurrent-models-with","title":"Exploring Deep Recurrent Models with Reinforcement Learning for Molecule Design","date":"2018-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-benchmarking-environment-for-reinforcement","title":"A Benchmarking Environment for Reinforcement Learning Based Task Oriented Dialogue Management","date":"2017-11-29","arxiv_id":"1711.11023","n_code_links":0,"syntology":null},{"paper":"/paper/ai-safety-gridworlds","slug":"ai-safety-gridworlds","title":"AI Safety Gridworlds","date":"2017-11-27","arxiv_id":"1711.09883","n_code_links":2,"syntology":null},{"paper":null,"slug":"adversarial-advantage-actor-critic-model-for","title":"Adversarial Advantage Actor-Critic Model for Task-Completion Dialogue Policy Learning","date":"2017-10-31","arxiv_id":"1710.11277","n_code_links":0,"syntology":null},{"paper":"/paper/treeqn-and-atreec-differentiable-tree","slug":"treeqn-and-atreec-differentiable-tree","title":"TreeQN and ATreeC: Differentiable Tree-Structured Models for Deep Reinforcement Learning","date":"2017-10-31","arxiv_id":"1710.11417","n_code_links":1,"syntology":{"ran":7,"of":12,"n_ran_checked":7,"n_instrument":0,"unverified":5,"pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["oxwhirl/treeqn"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/asynchronous-methods-for-deep-reinforcement","slug":"asynchronous-methods-for-deep-reinforcement","title":"Asynchronous Methods for Deep Reinforcement Learning","date":"2016-02-04","arxiv_id":"1602.01783","n_code_links":70,"syntology":{"ran":60,"of":95,"n_ran_checked":50,"n_instrument":10,"unverified":35,"pointer_only":20,"phrase":"60 ran (of which 20 constructed an object rather than computing a result; 50 with no instrument failure: 2 honoured, 1 violated, 47 with no contract checked; 10 where Syntology's instrument failed) · 35 unverified","official":null}}],"papers_shown":82,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":82,"with_a_code_link":27,"where_syntology_ran_a_sample":12,"not_listed_spam_title":0,"listed":82,"listed_where_code_ran":12,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":11,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":11,"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":12,"papers_where_code_ran_first_page":"/method/a2c/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":"ran","page":1,"of":1,"url":"/method/a2c/papers/ran/1","json":"/method/a2c/papers/ran/1.json","rows":12}],"tasks":[{"task":"/task/reinforcement-learning-1","name":"Reinforcement Learning (RL)","papers":52},{"task":"/task/reinforcement-learning-2","name":"reinforcement-learning","papers":50},{"task":"/task/reinforcement-learning","name":"Reinforcement Learning","papers":49},{"task":"/task/deep-reinforcement-learning","name":"Deep Reinforcement Learning","papers":30},{"task":"/task/decision-making","name":"Decision Making","papers":12},{"task":"/task/atari-games","name":"Atari Games","papers":10},{"task":"/task/q-learning","name":"Q-Learning","papers":7},{"task":"/task/continuous-control","name":"Continuous Control","papers":6},{"task":"/task/continuous-control","name":"continuous-control","papers":6},{"task":"/task/openai-gym","name":"OpenAI Gym","papers":5},{"task":"/task/benchmarking","name":"Benchmarking","papers":4},{"task":"/task/management","name":"Management","papers":4},{"task":"/task/representation-learning","name":"Representation Learning","papers":4},{"task":null,"name":"GPU","papers":3},{"task":"/task/mujoco","name":"MuJoCo","papers":3},{"task":"/task/multi-agent-reinforcement-learning","name":"Multi-agent Reinforcement Learning","papers":3},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":2},{"task":"/task/drug-discovery","name":"Drug Discovery","papers":2},{"task":"/task/language-modelling","name":"Language Modelling","papers":2},{"task":"/task/myocardial-infarction-detection","name":"Myocardial infarction detection","papers":2}],"tasks_shown":20,"n_tasks":86,"usage_by_year":[{"year":"2016","papers":1},{"year":"2017","papers":4},{"year":"2018","papers":8},{"year":"2019","papers":14},{"year":"2020","papers":10},{"year":"2021","papers":8},{"year":"2022","papers":10},{"year":"2023","papers":14},{"year":"2024","papers":9},{"year":"2025","papers":4}],"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/a2c"},"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=A2C","read_at":"2026-10-05T00:51:16+00:00","query":"A2C","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":"1602.01783","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 'A2C' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["KG-A2C","MORL-A2C","Larch-A2C","Diffusion A2C (DA2C)","Federated Temporal Graph Convolutional Network with Advantage Actor-Critic (Federated TGCN-A2C)"],"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":"4a292c89964205750583740015cd5572dc43e5a7fe56820ae02f7456ff3c71fd","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}