{"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/reinforce","slug":"reinforce","name":"REINFORCE","full_name":"REINFORCE","full_name_withheld":false,"description_markdown":"**REINFORCE** is a Monte Carlo variant of a policy gradient algorithm in reinforcement learning. The agent collects samples of an episode using its current policy, and uses it to update the policy parameter $\\theta$. Since one full trajectory must be completed to construct a sample space, it is updated as an off-policy algorithm.\r\n\r\n$$ \\nabla\\_{\\theta}J\\left(\\theta\\right) = \\mathbb{E}\\_{\\pi}\\left[G\\_{t}\\nabla\\_{\\theta}\\ln\\pi\\_{\\theta}\\left(A\\_{t}\\mid{S\\_{t}}\\right)\\right]$$\r\n\r\nImage Credit: [Tingwu Wang](http://www.cs.toronto.edu/~tingwuwang/REINFORCE.pdf)","description_state":"present","introduced_year":1999,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":null,"title":null,"url_on_a_paper_host":false},"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":185,"archive_num_papers":185,"papers_newest_first":[{"paper":null,"slug":"asymmetric-reinforce-for-off-policy","title":"Asymmetric REINFORCE for off-Policy Reinforcement Learning: Balancing positive and negative rewards","date":"2025-06-25","arxiv_id":"2506.20520","n_code_links":0,"syntology":null},{"paper":null,"slug":"quantum-fisher-preconditioned-reinforcement","title":"Quantum Fisher-Preconditioned Reinforcement Learning: From Single-Qubit Control to Rayleigh-Fading Link Adaptation","date":"2025-06-18","arxiv_id":"2506.15753","n_code_links":0,"syntology":null},{"paper":null,"slug":"zeroth-order-optimization-is-secretly-single","title":"Zeroth-Order Optimization is Secretly Single-Step Policy Optimization","date":"2025-06-17","arxiv_id":"2506.14460","n_code_links":0,"syntology":null},{"paper":null,"slug":"response-level-rewards-are-all-you-need-for","title":"Response-Level Rewards Are All You Need for Online Reinforcement Learning in LLMs: A Mathematical Perspective","date":"2025-06-03","arxiv_id":"2506.02553","n_code_links":0,"syntology":null},{"paper":null,"slug":"reordering-patches-improves-vision-models","title":"REOrdering Patches Improves Vision Models","date":"2025-05-29","arxiv_id":"2505.23751","n_code_links":0,"syntology":null},{"paper":null,"slug":"policy-gradient-with-second-order-momentum","title":"Policy Gradient with Second Order Momentum","date":"2025-05-16","arxiv_id":"2505.11561","n_code_links":0,"syntology":null},{"paper":null,"slug":"measures-of-variability-for-risk-averse","title":"Measures of Variability for Risk-averse Policy Gradient","date":"2025-04-15","arxiv_id":"2504.11412","n_code_links":0,"syntology":null},{"paper":null,"slug":"tapered-off-policy-reinforce-stable-and","title":"Tapered Off-Policy REINFORCE: Stable and efficient reinforcement learning for LLMs","date":"2025-03-18","arxiv_id":"2503.14286","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-fidelity-policy-gradient-algorithms","title":"Multi-Fidelity Policy Gradient Algorithms","date":"2025-03-07","arxiv_id":"2503.05696","n_code_links":0,"syntology":null},{"paper":null,"slug":"vqel-enabling-self-developed-symbolic","title":"VQEL: Enabling Self-Developed Symbolic Language in Agents through Vector Quantization in Emergent Language Games","date":"2025-03-06","arxiv_id":"2503.04940","n_code_links":0,"syntology":null},{"paper":"/paper/reinforce-adversarial-attacks-on-large","slug":"reinforce-adversarial-attacks-on-large","title":"REINFORCE Adversarial Attacks on Large Language Models: An Adaptive, Distributional, and Semantic Objective","date":"2025-02-24","arxiv_id":"2502.17254","n_code_links":1,"syntology":null},{"paper":null,"slug":"sample-complexity-of-linear-quadratic","title":"Sample Complexity of Linear Quadratic Regulator Without Initial Stability","date":"2025-02-20","arxiv_id":"2502.14210","n_code_links":0,"syntology":null},{"paper":null,"slug":"reinforce-ing-chemical-language-models-in","title":"REINFORCE-ING Chemical Language Models in Drug Design","date":"2025-01-27","arxiv_id":"2501.15971","n_code_links":0,"syntology":null},{"paper":"/paper/reinforce-a-simple-and-efficient-approach-for","slug":"reinforce-a-simple-and-efficient-approach-for","title":"REINFORCE++: A Simple and Efficient Approach for Aligning Large Language Models","date":"2025-01-04","arxiv_id":"2501.03262","n_code_links":5,"syntology":null},{"paper":null,"slug":"graph-attention-based-casual-discovery-with","title":"Graph-attention-based Casual Discovery with Trust Region-navigated Clipping Policy Optimization","date":"2024-12-27","arxiv_id":"2412.19578","n_code_links":0,"syntology":null},{"paper":null,"slug":"qe-ebm-using-quality-estimators-as-energy","title":"QE-EBM: Using Quality Estimators as Energy Loss for Machine Translation","date":"2024-10-14","arxiv_id":"2410.10228","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-divergence-measures-for-training-gflownets","title":"On Divergence Measures for Training GFlowNets","date":"2024-10-12","arxiv_id":"2410.09355","n_code_links":0,"syntology":null},{"paper":null,"slug":"taco-rl-task-aware-prompt-compression","title":"TACO-RL: Task Aware Prompt Compression Optimization with Reinforcement Learning","date":"2024-09-19","arxiv_id":"2409.13035","n_code_links":0,"syntology":null},{"paper":null,"slug":"quantum-inspired-reinforcement-learning-for","title":"Quantum-inspired Reinforcement Learning for Synthesizable Drug Design","date":"2024-09-13","arxiv_id":"2409.09183","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-augmentation-policies-from-a-model","title":"Automated Data Augmentation for Few-Shot Time Series Forecasting: A Reinforcement Learning Approach Guided by a Model Zoo","date":"2024-09-10","arxiv_id":"2409.06282","n_code_links":0,"syntology":null},{"paper":null,"slug":"quantfactor-reinforce-mining-steady-formulaic","title":"QuantFactor REINFORCE: Mining Steady Formulaic Alpha Factors with Variance-bounded REINFORCE","date":"2024-09-08","arxiv_id":"2409.05144","n_code_links":0,"syntology":null},{"paper":null,"slug":"reinforcement-learning-tutorial-and-survey","title":"Reinforcement Learning: Tutorial and Survey","date":"2024-07-18","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"model-free-distortion-canceling-and-control","title":"Model-free Distortion Canceling and Control of Quantum Devices","date":"2024-07-13","arxiv_id":"2407.09877","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-partial-survey-of-decentralized-cooperative","title":"An Initial Introduction to Cooperative Multi-Agent Reinforcement Learning","date":"2024-05-10","arxiv_id":"2405.06161","n_code_links":0,"syntology":null},{"paper":"/paper/proximal-curriculum-with-task-correlations","slug":"proximal-curriculum-with-task-correlations","title":"Proximal Curriculum with Task Correlations for Deep Reinforcement Learning","date":"2024-05-03","arxiv_id":"2405.02481","n_code_links":1,"syntology":null},{"paper":"/paper/finding-visual-task-vectors","slug":"finding-visual-task-vectors","title":"Finding Visual Task Vectors","date":"2024-04-08","arxiv_id":"2404.05729","n_code_links":1,"syntology":{"ran":2,"of":11,"n_ran_checked":0,"n_instrument":2,"unverified":9,"pointer_only":11,"phrase":"2 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; 2 where Syntology's instrument failed) · 9 unverified","official":{"repos":["alhojel/visual_task_vectors"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":9,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"towards-efficient-risk-sensitive-policy","title":"Towards Efficient Risk-Sensitive Policy Gradient: An Iteration Complexity Analysis","date":"2024-03-13","arxiv_id":"2403.08955","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-multi-hop-knowledge-graph-reasoning","title":"Enhancing Multi-Hop Knowledge Graph Reasoning through Reward Shaping Techniques","date":"2024-03-09","arxiv_id":"2403.05801","n_code_links":0,"syntology":null},{"paper":"/paper/re3val-reinforced-and-reranked-generative","slug":"re3val-reinforced-and-reranked-generative","title":"Re3val: Reinforced and Reranked Generative Retrieval","date":"2024-01-30","arxiv_id":"2401.16979","n_code_links":0,"syntology":{"ran":10,"of":13,"n_ran_checked":7,"n_instrument":3,"unverified":3,"pointer_only":13,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 2 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":null,"slug":"quantum-architecture-search-with-unsupervised","title":"Quantum Architecture Search with Unsupervised Representation Learning","date":"2024-01-21","arxiv_id":"2401.11576","n_code_links":0,"syntology":null},{"paper":null,"slug":"carss-cooperative-attention-guided","title":"CARSS: Cooperative Attention-guided Reinforcement Subpath Synthesis for Solving Traveling Salesman Problem","date":"2023-12-24","arxiv_id":"2312.15412","n_code_links":0,"syntology":null},{"paper":"/paper/response-enhanced-semi-supervised-dialogue","slug":"response-enhanced-semi-supervised-dialogue","title":"Response Enhanced Semi-supervised Dialogue Query Generation","date":"2023-12-20","arxiv_id":"2312.12713","n_code_links":1,"syntology":null},{"paper":null,"slug":"differentiable-sampling-of-categorical","title":"Differentiable Sampling of Categorical Distributions Using the CatLog-Derivative Trick","date":"2023-11-21","arxiv_id":"2311.12569","n_code_links":0,"syntology":null},{"paper":null,"slug":"taming-gradient-variance-in-federated","title":"Taming Gradient Variance in Federated Learning with Networked Control Variates","date":"2023-10-26","arxiv_id":"2310.17200","n_code_links":0,"syntology":null},{"paper":"/paper/remax-a-simple-effective-and-efficient-method","slug":"remax-a-simple-effective-and-efficient-method","title":"ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models","date":"2023-10-16","arxiv_id":"2310.10505","n_code_links":3,"syntology":{"ran":11,"of":13,"n_ran_checked":9,"n_instrument":2,"unverified":2,"pointer_only":13,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["liziniu/ReMax"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/would-i-have-gotten-that-reward-long-term","slug":"would-i-have-gotten-that-reward-long-term","title":"Would I have gotten that reward? Long-term credit assignment by counterfactual contribution analysis","date":"2023-09-21","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/reinforcement-learning-for-sampling-on","slug":"reinforcement-learning-for-sampling-on","title":"Reinforcement Learning for Sampling on Temporal Medical Imaging Sequences","date":"2023-08-28","arxiv_id":"2308.14946","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["zhishenhuang/rlsamp"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/training-normalizing-flows-with","slug":"training-normalizing-flows-with","title":"Training normalizing flows with computationally intensive target probability distributions","date":"2023-08-25","arxiv_id":"2308.13294","n_code_links":1,"syntology":null},{"paper":null,"slug":"desiderata-for-normative-models-of-synaptic","title":"Desiderata for normative models of synaptic plasticity","date":"2023-08-09","arxiv_id":"2308.04988","n_code_links":0,"syntology":null},{"paper":"/paper/esrl-efficient-sampling-based-reinforcement","slug":"esrl-efficient-sampling-based-reinforcement","title":"ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation","date":"2023-08-04","arxiv_id":"2308.02223","n_code_links":2,"syntology":{"ran":12,"of":14,"n_ran_checked":11,"n_instrument":1,"unverified":2,"pointer_only":3,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["wangclnlp/DeepSpeed-Chat-Extension"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"structural-credit-assignment-with-coordinated","title":"Structural Credit Assignment with Coordinated Exploration","date":"2023-07-25","arxiv_id":"2307.13256","n_code_links":0,"syntology":null},{"paper":null,"slug":"unbiased-weight-maximization","title":"Unbiased Weight Maximization","date":"2023-07-25","arxiv_id":"2307.13270","n_code_links":0,"syntology":null},{"paper":"/paper/meta-value-learning-a-general-framework-for","slug":"meta-value-learning-a-general-framework-for","title":"Meta-Value Learning: a General Framework for Learning with Learning Awareness","date":"2023-07-17","arxiv_id":"2307.08863","n_code_links":1,"syntology":null},{"paper":null,"slug":"ada-nav-adaptive-trajectory-based-sample","title":"Confidence-Controlled Exploration: Efficient Sparse-Reward Policy Learning for Robot Navigation","date":"2023-06-09","arxiv_id":"2306.06192","n_code_links":0,"syntology":null},{"paper":"/paper/reinforcement-learning-for-topic-models","slug":"reinforcement-learning-for-topic-models","title":"Reinforcement Learning for Topic Models","date":"2023-05-08","arxiv_id":"2305.04843","n_code_links":1,"syntology":null},{"paper":"/paper/optimization-of-binding-affinities-in","slug":"optimization-of-binding-affinities-in","title":"Optimization of binding affinities in chemical space with generative pretrained transformer and deep reinforcement learning","date":"2023-04-03","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"ch-go-online-go-system-based-on-chunk-data","title":"CH-Go: Online Go System Based on Chunk Data Storage","date":"2023-03-22","arxiv_id":"2303.13553","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-start-team-orienteering-problem-for-uas","title":"Multi-Start Team Orienteering Problem for UAS Mission Re-Planning with Data-Efficient Deep Reinforcement Learning","date":"2023-03-02","arxiv_id":"2303.01963","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-global-convergence-of-risk-averse","title":"On the Global Convergence of Risk-Averse Policy Gradient Methods with Expected Conditional Risk Measures","date":"2023-01-26","arxiv_id":"2301.10932","n_code_links":0,"syntology":null},{"paper":"/paper/lightweight-neural-architecture-search-for","slug":"lightweight-neural-architecture-search-for","title":"Lightweight Neural Architecture Search for Temporal Convolutional Networks at the Edge","date":"2023-01-24","arxiv_id":"2301.10281","n_code_links":1,"syntology":null},{"paper":"/paper/nas-lid-efficient-neural-architecture-search","slug":"nas-lid-efficient-neural-architecture-search","title":"NAS-LID: Efficient Neural Architecture Search with Local Intrinsic Dimension","date":"2022-11-23","arxiv_id":"2211.12759","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-latent-part-whole-hierarchies-for","title":"Learning Latent Part-Whole Hierarchies for Point Clouds","date":"2022-11-14","arxiv_id":"2211.07082","n_code_links":0,"syntology":null},{"paper":"/paper/neuroprim-an-attention-based-model-for","slug":"neuroprim-an-attention-based-model-for","title":"NeuroPrim: An Attention-based Model for Solving NP-hard Spanning Tree Problems","date":"2022-10-22","arxiv_id":"2210.12453","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-convergence-of-policy-gradient-methods","title":"On the convergence of policy gradient methods to Nash equilibria in general stochastic games","date":"2022-10-17","arxiv_id":"2210.08857","n_code_links":0,"syntology":null},{"paper":null,"slug":"reward-shaping-for-user-satisfaction-in-a","title":"Reward Shaping for User Satisfaction in a REINFORCE Recommender","date":"2022-09-30","arxiv_id":"2209.15166","n_code_links":0,"syntology":null},{"paper":null,"slug":"fast-offline-policy-optimization-for-large","title":"Fast Offline Policy Optimization for Large Scale Recommendation","date":"2022-08-08","arxiv_id":"2208.05327","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-representation-modeling-based-language-gan","title":"InitialGAN: A Language GAN with Completely Random Initialization","date":"2022-08-04","arxiv_id":"2208.02531","n_code_links":0,"syntology":null},{"paper":null,"slug":"mad-for-robust-reinforcement-learning-in-1","title":"MAD for Robust Reinforcement Learning in Machine Translation","date":"2022-07-18","arxiv_id":"2207.08583","n_code_links":0,"syntology":null},{"paper":null,"slug":"bypass-network-for-semantics-driven-image","title":"Bypass Network for Semantics Driven Image Paragraph Captioning","date":"2022-06-21","arxiv_id":"2206.10059","n_code_links":0,"syntology":null},{"paper":"/paper/agnas-attention-guided-micro-and-macro","slug":"agnas-attention-guided-micro-and-macro","title":"AGNAS: Attention-Guided Micro- and Macro-Architecture Search","date":"2022-06-05","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"search-space-adaptation-for-differentiable","title":"Search Space Adaptation for Differentiable Neural Architecture Search in Image Classification","date":"2022-06-05","arxiv_id":"2206.02098","n_code_links":0,"syntology":null},{"paper":"/paper/probabilistic-permutation-graph-search-black","slug":"probabilistic-permutation-graph-search-black","title":"Probabilistic Permutation Graph Search: Black-Box Optimization for Fairness in Ranking","date":"2022-04-28","arxiv_id":"2204.13765","n_code_links":1,"syntology":null},{"paper":"/paper/post-processing-recommender-systems-with","slug":"post-processing-recommender-systems-with","title":"Post Processing Recommender Systems with Knowledge Graphs for Recency, Popularity, and Diversity of Explanations","date":"2022-04-24","arxiv_id":"2204.11241","n_code_links":1,"syntology":null},{"paper":null,"slug":"ma-dreamer-coordination-and-communication","title":"MA-Dreamer: Coordination and communication through shared imagination","date":"2022-04-10","arxiv_id":"2204.04687","n_code_links":0,"syntology":null},{"paper":"/paper/selecting-optimal-context-sentences-for-event","slug":"selecting-optimal-context-sentences-for-event","title":"Selecting Optimal Context Sentences for Event-Event Relation Extraction","date":"2022-04-02","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/generalizing-few-shot-nas-with-gradient-1","slug":"generalizing-few-shot-nas-with-gradient-1","title":"Generalizing Few-Shot NAS with Gradient Matching","date":"2022-03-29","arxiv_id":"2203.15207","n_code_links":1,"syntology":{"ran":3,"of":7,"n_ran_checked":3,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["skhu101/GM-NAS"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"merlin-malware-evasion-with-reinforcement","title":"MERLIN -- Malware Evasion with Reinforcement LearnINg","date":"2022-03-24","arxiv_id":"2203.12980","n_code_links":0,"syntology":null},{"paper":"/paper/safe-neurosymbolic-learning-with","slug":"safe-neurosymbolic-learning-with","title":"Safe Neurosymbolic Learning with Differentiable Symbolic Execution","date":"2022-03-15","arxiv_id":"2203.07671","n_code_links":2,"syntology":null},{"paper":null,"slug":"towards-tailored-models-on-private-aiot","title":"Towards Tailored Models on Private AIoT Devices: Federated Direct Neural Architecture Search","date":"2022-02-23","arxiv_id":"2202.11490","n_code_links":0,"syntology":null},{"paper":"/paper/gradient-estimation-with-discrete-stein","slug":"gradient-estimation-with-discrete-stein","title":"Gradient Estimation with Discrete Stein Operators","date":"2022-02-19","arxiv_id":"2202.09497","n_code_links":1,"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":["thjashin/rodeo"],"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":"data-free-neural-architecture-search-via","title":"Data-Free Neural Architecture Search via Recursive Label Calibration","date":"2021-12-03","arxiv_id":"2112.02086","n_code_links":0,"syntology":null},{"paper":null,"slug":"structural-credit-assignment-in-neural","title":"Structural Credit Assignment in Neural Networks using Reinforcement Learning","date":"2021-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"mad-for-robust-reinforcement-learning-in","title":"MAD for Robust Reinforcement Learning in Machine Translation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/double-control-variates-for-gradient","slug":"double-control-variates-for-gradient","title":"Double Control Variates for Gradient Estimation in Discrete Latent Variable Models","date":"2021-11-09","arxiv_id":"2111.05300","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":{"repos":["thjashin/double-cv"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/carms-categorical-antithetic-reinforce-multi","slug":"carms-categorical-antithetic-reinforce-multi","title":"CARMS: Categorical-Antithetic-REINFORCE Multi-Sample Gradient Estimator","date":"2021-10-26","arxiv_id":"2110.14002","n_code_links":1,"syntology":null},{"paper":null,"slug":"hindsight-network-credit-assignment-efficient","title":"Hindsight Network Credit Assignment: Efficient Credit Assignment in Networks of Discrete Stochastic Units","date":"2021-10-14","arxiv_id":"2110.07700","n_code_links":0,"syntology":null},{"paper":"/paper/improving-the-sample-efficiency-of-neural","slug":"improving-the-sample-efficiency-of-neural","title":"Improving the sample-efficiency of neural architecture search with reinforcement learning","date":"2021-10-13","arxiv_id":"2110.06751","n_code_links":1,"syntology":null},{"paper":"/paper/profiling-neural-blocks-and-design-spaces-for","slug":"profiling-neural-blocks-and-design-spaces-for","title":"Profiling Neural Blocks and Design Spaces for Mobile Neural Architecture Search","date":"2021-09-25","arxiv_id":"2109.12426","n_code_links":1,"syntology":null},{"paper":"/paper/regen-reinforcement-learning-for-text-and","slug":"regen-reinforcement-learning-for-text-and","title":"ReGen: Reinforcement Learning for Text and Knowledge Base Generation using Pretrained Language Models","date":"2021-08-27","arxiv_id":"2108.12472","n_code_links":1,"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":["IBM/regen"],"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/semantic-based-self-critical-training-for","slug":"semantic-based-self-critical-training-for","title":"Semantic-Based Self-Critical Training For Question Generation","date":"2021-08-26","arxiv_id":"2108.12026","n_code_links":1,"syntology":null},{"paper":"/paper/aspect-sentiment-triplet-extraction-using","slug":"aspect-sentiment-triplet-extraction-using","title":"Aspect Sentiment Triplet Extraction Using Reinforcement Learning","date":"2021-08-13","arxiv_id":"2108.06107","n_code_links":1,"syntology":null},{"paper":null,"slug":"boosting-video-captioning-with-dynamic-loss","title":"Boosting Video Captioning with Dynamic Loss Network","date":"2021-07-25","arxiv_id":"2107.11707","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-general-sample-complexity-analysis-of","title":"A general sample complexity analysis of vanilla policy gradient","date":"2021-07-23","arxiv_id":"2107.11433","n_code_links":0,"syntology":null},{"paper":null,"slug":"federated-model-search-via-reinforcement","title":"Federated Model Search via Reinforcement Learning","date":"2021-07-07","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"inverse-design-of-grating-couplers-using-the","title":"Inverse Design of Grating Couplers Using the Policy Gradient Method from Reinforcement Learning","date":"2021-06-30","arxiv_id":"2107.00088","n_code_links":0,"syntology":null},{"paper":null,"slug":"curious-explorer-a-provable-exploration","title":"Curious Explorer: a provable exploration strategy in Policy Learning","date":"2021-06-29","arxiv_id":"2106.15503","n_code_links":0,"syntology":null},{"paper":null,"slug":"coupled-gradient-estimators-for-discrete","title":"Coupled Gradient Estimators for Discrete Latent Variables","date":"2021-06-15","arxiv_id":"2106.08056","n_code_links":0,"syntology":null},{"paper":"/paper/arms-antithetic-reinforce-multi-sample","slug":"arms-antithetic-reinforce-multi-sample","title":"ARMS: Antithetic-REINFORCE-Multi-Sample Gradient for Binary Variables","date":"2021-05-28","arxiv_id":"2105.14141","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":["alekdimi/arms"],"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":null,"slug":"generative-adversarial-neural-architecture-1","title":"Generative Adversarial Neural Architecture Search","date":"2021-05-19","arxiv_id":"2105.09356","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-content-provider-aware-recommender","title":"Towards Content Provider Aware Recommender Systems: A Simulation Study on the Interplay between User and Provider Utilities","date":"2021-05-06","arxiv_id":"2105.02377","n_code_links":0,"syntology":null},{"paper":"/paper/hard-attention-for-scalable-image","slug":"hard-attention-for-scalable-image","title":"Hard-Attention for Scalable Image Classification","date":"2021-02-20","arxiv_id":"2102.10212","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-convergence-and-sample-efficiency-of","title":"On the Convergence and Sample Efficiency of Variance-Reduced Policy Gradient Method","date":"2021-02-17","arxiv_id":"2102.08607","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-as-i-mean-not-as-i-say-sequence-loss","title":"Do as I mean, not as I say: Sequence Loss Training for Spoken Language Understanding","date":"2021-02-12","arxiv_id":"2102.06750","n_code_links":0,"syntology":null},{"paper":"/paper/deep-reinforcement-agent-for-scheduling-in","slug":"deep-reinforcement-agent-for-scheduling-in","title":"Deep Reinforcement Agent for Scheduling in HPC","date":"2021-02-11","arxiv_id":"2102.06243","n_code_links":1,"syntology":null},{"paper":null,"slug":"reinforcement-learning-based-recommender-1","title":"Reinforcement learning based recommender systems: A survey","date":"2021-01-15","arxiv_id":"2101.06286","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploration-of-visual-features-and-their","title":"Exploration of Visual Features and their weighted-additive fusion for Video Captioning","date":"2021-01-14","arxiv_id":"2101.05806","n_code_links":0,"syntology":null},{"paper":null,"slug":"smoothed-functional-based-gradient-algorithms","title":"Smoothed functional-based gradient algorithms for off-policy reinforcement learning: A non-asymptotic viewpoint","date":"2021-01-06","arxiv_id":"2101.02137","n_code_links":0,"syntology":null},{"paper":"/paper/generalized-latency-performance-estimation","slug":"generalized-latency-performance-estimation","title":"Generalized Latency Performance Estimation for Once-For-All Neural Architecture Search","date":"2021-01-04","arxiv_id":"2101.00732","n_code_links":2,"syntology":null},{"paper":null,"slug":"learning-to-solve-multi-robot-task-allocation","title":"Learning to Solve Multi-Robot Task Allocation with a Covariant-Attention based Neural Architecture","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"reinforcement-learning-for-control-with","title":"Reinforcement Learning for Control with Probabilistic Stability Guarantee","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null}],"papers_shown":100,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":185,"with_a_code_link":80,"where_syntology_ran_a_sample":24,"not_listed_spam_title":0,"listed":185,"listed_where_code_ran":24,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":20,"every_run_a_failure_of_syntologys_instrument":4,"listed_with_a_run_with_no_instrument_failure":20,"listed_every_run_a_failure_of_syntologys_instrument":4,"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":24,"papers_where_code_ran_first_page":"/method/reinforce/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/reinforce/papers/2","json":"/method/reinforce/papers/2.json","rows":85},{"order":"ran","page":1,"of":1,"url":"/method/reinforce/papers/ran/1","json":"/method/reinforce/papers/ran/1.json","rows":24}],"tasks":[{"task":"/task/reinforcement-learning-1","name":"Reinforcement Learning (RL)","papers":59},{"task":"/task/reinforcement-learning","name":"Reinforcement Learning","papers":43},{"task":"/task/reinforcement-learning-2","name":"reinforcement-learning","papers":42},{"task":"/task/architecture-search","name":"Neural Architecture Search","papers":19},{"task":"/task/policy-gradient-methods","name":"Policy Gradient Methods","papers":16},{"task":"/task/deep-reinforcement-learning","name":"Deep Reinforcement Learning","papers":12},{"task":"/task/text-generation","name":"Text Generation","papers":9},{"task":"/task/diversity","name":"Diversity","papers":8},{"task":"/task/sentence","name":"Sentence","papers":8},{"task":"/task/image-classification","name":"Image Classification","papers":7},{"task":"/task/q-learning","name":"Q-Learning","papers":7},{"task":"/task/question-answering","name":"Question Answering","papers":7},{"task":"/task/decision-making","name":"Decision Making","papers":6},{"task":null,"name":"GPU","papers":6},{"task":"/task/image-captioning","name":"Image Captioning","papers":5},{"task":"/task/machine-translation","name":"Machine Translation","papers":5},{"task":"/task/recommendation-systems","name":"Recommendation Systems","papers":5},{"task":"/task/translation","name":"Translation","papers":5},{"task":"/task/image-classification","name":"image-classification","papers":5},{"task":"/task/bayesian-optimization","name":"Bayesian Optimization","papers":4}],"tasks_shown":20,"n_tasks":167,"usage_by_year":[{"year":"2011","papers":1},{"year":"2013","papers":1},{"year":"2015","papers":1},{"year":"2016","papers":6},{"year":"2017","papers":9},{"year":"2018","papers":18},{"year":"2019","papers":18},{"year":"2020","papers":31},{"year":"2021","papers":30},{"year":"2022","papers":20},{"year":"2023","papers":20},{"year":"2024","papers":16},{"year":"2025","papers":14}],"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/reinforce"},"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=REINFORCE","read_at":"2026-10-05T01:01:02+00:00","query":"REINFORCE","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":null,"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 'REINFORCE' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["L-REINFORCE","MF-REINFORCE","Buffer-and-Reinforce","Ground-Compose-Reinforce","Reinforce Adjoint Matching (RAM)"],"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":"a754d272886c490cd49c12dd94190cea5b081cf87eda3283ed4fa1e88de92cc6","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}