{"total":42,"rows":[{"id":"2110.05038","title":"Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs","created":"2021-10-11","cited_by_count":122,"area":null},{"id":"2111.13485","title":"Learning Long-Term Reward Redistribution via Randomized Return Decomposition","created":"2021-11-26","cited_by_count":33,"area":null},{"id":"2102.12425","title":"Synthetic Returns for Long-Term Credit Assignment","created":"2021-02-24","cited_by_count":27,"area":null},{"id":"2103.06224","title":"An Information-Theoretic Perspective on Credit Assignment in Reinforcement Learning","created":"2021-03-10","cited_by_count":20,"area":null},{"id":"2205.14345","title":"Reinforcement Learning for Branch-and-Bound Optimisation using Retrospective Trajectories","created":"2022-05-28","cited_by_count":20,"area":null},{"id":"2211.15457","title":"Hypernetworks for Zero-shot Transfer in Reinforcement Learning","created":"2022-11-28","cited_by_count":19,"area":null},{"id":"2306.13945","title":"Large Sequence Models for Sequential Decision-Making: A Survey","created":"2023-06-24","cited_by_count":19,"area":null},{"id":"2210.11846","title":"Redefining Counterfactual Explanations for Reinforcement Learning: Overview, Challenges and Opportunities","created":"2022-10-21","cited_by_count":13,"area":null},{"id":"2306.16803","title":"Would I have gotten that reward? Long-term credit assignment by counterfactual contribution analysis","created":"2023-06-29","cited_by_count":13,"area":null},{"id":"2204.00302","title":"Actual Causality and Responsibility Attribution in Decentralized Partially Observable Markov Decision Processes","created":"2022-04-01","cited_by_count":8,"area":null},{"id":"2203.08542","title":"Lazy-MDPs: Towards Interpretable Reinforcement Learning by Learning When to Act","created":"2022-03-16","cited_by_count":7,"area":null},{"id":"2106.06508","title":"Preferential Temporal Difference Learning","created":"2021-06-11","cited_by_count":6,"area":null},{"id":"2108.02096","title":"Policy Gradients Incorporating the Future","created":"2021-08-04","cited_by_count":6,"area":null},{"id":"2607.00871","title":"Self-Evolving Agents with Anytime-Valid Certificates","created":"2026-07-01","cited_by_count":6,"area":null},{"id":"2106.04499","title":"Towards Practical Credit Assignment for Deep Reinforcement Learning","created":"2021-06-08","cited_by_count":5,"area":null},{"id":"2609.04094","title":"DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training","created":"2026-09-03","cited_by_count":5,"area":null},{"id":"2202.09699","title":"Selective Credit Assignment","created":"2022-02-20","cited_by_count":4,"area":null},{"id":"2211.10515","title":"Curiosity in Hindsight: Intrinsic Exploration in Stochastic Environments","created":"2022-11-18","cited_by_count":4,"area":null},{"id":"2307.11897","title":"Hindsight-DICE: Stable Credit Assignment for Deep Reinforcement Learning","created":"2023-07-21","cited_by_count":4,"area":null},{"id":"2606.16285","title":"HiMPO: Hindsight-Informed Memory Policy Optimization for Less-Entangled Credit in Long-Horizon Agents","created":"2026-06-15","cited_by_count":4,"area":null},{"id":"2211.06665","title":"A Survey on Explainable Reinforcement Learning: Concepts, Algorithms, Challenges","created":"2022-11-12","cited_by_count":3,"area":null},{"id":"2301.10289","title":"PushWorld: A benchmark for manipulation planning with tools and movable obstacles","created":"2023-01-24","cited_by_count":3,"area":null},{"id":"2407.04451","title":"Hindsight Preference Learning for Offline Preference-based Reinforcement Learning","created":"2024-07-05","cited_by_count":3,"area":null},{"id":"2102.04999","title":"Adaptive Pairwise Weights for Temporal Credit Assignment","created":"2021-02-09","cited_by_count":2,"area":null},{"id":"2201.05819","title":"Interpretable and Effective Reinforcement Learning for Attacking against Graph-based Rumor Detection","created":"2022-01-15","cited_by_count":2,"area":null},{"id":"2312.10642","title":"Episodic Return Decomposition by Difference of Implicitly Assigned Sub-Trajectory Reward","created":"2023-12-17","cited_by_count":2,"area":null},{"id":"2604.12007","title":"When to Forget: A Memory Governance Primitive","created":"2026-04-13","cited_by_count":2,"area":null},{"id":"2608.01321","title":"BiCAA: Bidirectional Credit Assignment for Search-Augmented Agent","created":"2026-08-02","cited_by_count":2,"area":null},{"id":"2412.14779","title":"Agent-Temporal Credit Assignment for Optimal Policy Preservation in Sparse Multi-Agent Reinforcement Learning","created":"2024-12-19","cited_by_count":1,"area":null},{"id":"2506.13803","title":"Causality in the human niche: lessons for machine learning","created":"2025-06-13","cited_by_count":1,"area":null},{"id":"2511.15716","title":"MACIE: Multi-Agent Causal Intelligence Explainer for Collective Behavior Understanding","created":"2025-11-11","cited_by_count":1,"area":null},{"id":"2103.02265","title":"Meta-Learning with Variational Bayes","created":"2021-03-03","cited_by_count":0,"area":null},{"id":"2110.07700","title":"Hindsight Network Credit Assignment: Efficient Credit Assignment in Networks of Discrete Stochastic Units","created":"2021-10-14","cited_by_count":0,"area":null},{"id":"2111.08435","title":"Free Will Belief as a consequence of Model-based Reinforcement Learning","created":"2021-11-14","cited_by_count":0,"area":null},{"id":"2306.01896","title":"Learning to Stabilize Online Reinforcement Learning in Unbounded State Spaces","created":"2023-06-02","cited_by_count":0,"area":null},{"id":"2310.08100","title":"Generative Intrinsic Optimization: Intrinsic Control with Model Learning","created":"2023-10-12","cited_by_count":0,"area":null},{"id":"2401.00162","title":"Policy Optimization with Smooth Guidance Learned from State-Only Demonstrations","created":"2023-12-30","cited_by_count":0,"area":null},{"id":"2502.04864","title":"Redistributing Rewards Across Time and Agents for Multi-Agent Reinforcement Learning","created":"2025-02-07","cited_by_count":0,"area":null},{"id":"2510.04676","title":"Counterfactual Credit Guided Bayesian Optimization","created":"2025-10-06","cited_by_count":0,"area":null},{"id":"2609.24985","title":"Critical-State RL: Diagnosing Trainable States for Multi-Turn Tool Use","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.26355","title":"PACT: From Credit Assignment to Critic Alignment","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.37930","title":"Learning What to Remember: Long-horizon Counterfactual Memory Optimization","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}