{"total":58,"rows":[{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546,"area":"offlinerl"},{"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":"2509.21240","title":"Tree Search for LLM Agent Reinforcement Learning","created":"2025-09-25","cited_by_count":79,"area":"agents"},{"id":"2307.03864","title":"When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment","created":"2023-07-07","cited_by_count":63,"area":null},{"id":"2105.14039","title":"Towards mental time travel: a hierarchical memory for reinforcement learning agents","created":"2021-05-28","cited_by_count":40,"area":null},{"id":"2403.04253","title":"Mastering Memory Tasks with World Models","created":"2024-03-07","cited_by_count":38,"area":"wm"},{"id":"2502.10550","title":"Memory, Benchmark & Robots: A Benchmark for Solving Complex Tasks with Reinforcement Learning","created":"2025-02-14","cited_by_count":36,"area":"deeprl"},{"id":"2102.12425","title":"Synthetic Returns for Long-Term Credit Assignment","created":"2021-02-24","cited_by_count":27,"area":null},{"id":"2306.05167","title":"Decision S4: Efficient Sequence-Based RL via State Spaces Layers","created":"2023-06-08","cited_by_count":26,"area":"offlinerl"},{"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":"2408.14336","title":"Equivariant Reinforcement Learning under Partial Observability","created":"2024-08-26","cited_by_count":18,"area":"deeprl"},{"id":"2112.09477","title":"Learning Reward Machines: A Study in Partially Observable Reinforcement Learning","created":"2021-12-17","cited_by_count":16,"area":null},{"id":"2111.02104","title":"Model-Based Episodic Memory Induces Dynamic Hybrid Controls","created":"2021-11-03","cited_by_count":14,"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":"2307.05979","title":"Transformers in Reinforcement Learning: A Survey","created":"2023-07-12","cited_by_count":12,"area":null},{"id":"2506.00744","title":"Blending Complementary Memory Systems in Hybrid Quadratic-Linear Transformers","created":"2025-05-31","cited_by_count":12,"area":null},{"id":"2207.13649","title":"Explain My Surprise: Learning Efficient Long-Term Memory by Predicting Uncertain Outcomes","created":"2022-07-27","cited_by_count":11,"area":null},{"id":"2501.13075","title":"Evolution and The Knightian Blindspot of Machine Learning","created":"2025-01-22","cited_by_count":11,"area":null},{"id":"2402.05290","title":"Do Transformer World Models Give Better Policy Gradients?","created":"2024-02-07","cited_by_count":10,"area":"wm"},{"id":"2405.17358","title":"Rethinking Transformers in Solving POMDPs","created":"2024-05-27","cited_by_count":9,"area":"deeprl"},{"id":"2410.10132","title":"Stable Hadamard Memory: Revitalizing Memory-Augmented Agents for Reinforcement Learning","created":"2024-10-14","cited_by_count":9,"area":"deeprl"},{"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":"2409.12798","title":"Assessing the Zero-Shot Capabilities of LLMs for Action Evaluation in RL","created":"2024-09-19","cited_by_count":7,"area":null},{"id":"2411.00722","title":"Token-level Proximal Policy Optimization for Query Generation","created":"2024-11-01","cited_by_count":7,"area":"alignment"},{"id":"2106.06508","title":"Preferential Temporal Difference Learning","created":"2021-06-11","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":"2112.01853","title":"Episodic Policy Gradient Training","created":"2021-12-03","cited_by_count":5,"area":null},{"id":"2402.15160","title":"Spatially-Aware Transformer for Embodied Agents","created":"2024-02-23","cited_by_count":5,"area":"deeprl"},{"id":"2410.15885","title":"VLASCD: A Visual Language Action Model for Simultaneous Chatting and Decision Making","created":"2024-10-21","cited_by_count":5,"area":null},{"id":"2202.09699","title":"Selective Credit Assignment","created":"2022-02-20","cited_by_count":4,"area":null},{"id":"2210.05845","title":"Contrastive Retrospection: honing in on critical steps for rapid learning and generalization in RL","created":"2022-10-12","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":"2407.12437","title":"Variable-Agnostic Causal Exploration for Reinforcement Learning","created":"2024-07-17","cited_by_count":4,"area":"deeprl"},{"id":"2410.15184","title":"Action abstractions for amortized sampling","created":"2024-10-19","cited_by_count":4,"area":"deeprl"},{"id":"2204.02268","title":"Learning to Bid Long-Term: Multi-Agent Reinforcement Learning with Long-Term and Sparse Reward in Repeated Auction Games","created":"2022-04-05","cited_by_count":3,"area":null},{"id":"2512.19154","title":"Beyond Sliding Windows: Learning to Manage Memory in Non-Markovian Environments","created":"2025-12-22","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":"2307.05793","title":"Grid Cell-Inspired Fragmentation and Recall for Efficient Map Building","created":"2023-07-11","cited_by_count":2,"area":null},{"id":"2310.17537","title":"Neuro-Inspired Fragmentation and Recall to Overcome Catastrophic Forgetting in Curiosity","created":"2023-10-26","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":"2107.03015","title":"Evaluating the progress of Deep Reinforcement Learning in the real world: aligning domain-agnostic and domain-specific research","created":"2021-07-07","cited_by_count":1,"area":null},{"id":"2201.05464","title":"Bayesian sense of time in biological and artificial brains","created":"2022-01-14","cited_by_count":1,"area":null},{"id":"2205.06485","title":"Modeling Human Behavior Part I -- Learning and Belief Approaches","created":"2022-05-13","cited_by_count":1,"area":null},{"id":"2205.13718","title":"Off-Beat Multi-Agent Reinforcement Learning","created":"2022-05-27","cited_by_count":1,"area":null},{"id":"2310.02405","title":"PCGPT: Procedural Content Generation via Transformers","created":"2023-10-03","cited_by_count":1,"area":"offlinerl"},{"id":"2505.20579","title":"The challenge of hidden gifts in multi-agent reinforcement learning","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2506.01442","title":"Agentic Episodic Control","created":"2025-06-02","cited_by_count":1,"area":"agents"},{"id":"2603.06813","title":"Reinforcing the World's Edge: A Continual Learning Problem in the Multi-Agent-World Boundary","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2102.10527","title":"Delayed Rewards Calibration via Reward Empirical Sufficiency","created":"2021-02-21","cited_by_count":0,"area":null},{"id":"2208.04237","title":"Multi-Agent Reinforcement Learning for Long-Term Network Resource Allocation through Auction: a V2X Application","created":"2022-07-29","cited_by_count":0,"area":null},{"id":"2209.13489","title":"Reward Learning using Structural Motifs in Inverse Reinforcement Learning","created":"2022-09-25","cited_by_count":0,"area":"offlinerl"},{"id":"2308.10230","title":"Karma: Adaptive Video Streaming via Causal Sequence Modeling","created":"2023-08-20","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":"2604.04983","title":"Territory Paint Wars: Diagnosing and Mitigating Failure Modes in Competitive Multi-Agent PPO","created":"2026-04-04","cited_by_count":0,"area":null},{"id":"2606.21136","title":"Horizon Adaptive Offline Policy Learning via Value Stitching","created":"2026-06-19","cited_by_count":0,"area":"offlinerl"},{"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},{"id":"2610.13504","title":"Beyond Temporal Proximity: Explanatory World Models for Credit Assignment in Reinforcement Learning","created":"2026-10-09","cited_by_count":0,"area":"wm"}],"next_cursor":null}