{"total":64,"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":"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":"2210.11287","title":"MoCoDA: Model-based Counterfactual Data Augmentation","created":"2022-10-20","cited_by_count":44,"area":"offlinerl"},{"id":"2302.02228","title":"Counterfactual Identifiability of Bijective Causal Models","created":"2023-02-04","cited_by_count":43,"area":null},{"id":"2102.12425","title":"Synthetic Returns for Long-Term Credit Assignment","created":"2021-02-24","cited_by_count":27,"area":null},{"id":"2207.06272","title":"Hindsight Learning for MDPs with Exogenous Inputs","created":"2022-07-13","cited_by_count":26,"area":null},{"id":"2102.09407","title":"Adaptive Rational Activations to Boost Deep Reinforcement Learning","created":"2021-02-18","cited_by_count":23,"area":null},{"id":"2307.01452","title":"Causal Reinforcement Learning: A Survey","created":"2023-07-04","cited_by_count":23,"area":null},{"id":"2401.05821","title":"Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents","created":"2024-01-11","cited_by_count":23,"area":"deeprl"},{"id":"2606.08275","title":"Causal Agent Replay: Counterfactual Attribution for LLM-Agent Failures","created":"2026-06-06","cited_by_count":20,"area":"agents"},{"id":"2305.18427","title":"Interpretable Reward Redistribution in Reinforcement Learning: A Causal Approach","created":"2023-05-28","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":"2301.09031","title":"Counterfactual (Non-)identifiability of Learned Structural Causal Models","created":"2023-01-22","cited_by_count":17,"area":null},{"id":"2204.05133","title":"On the link between conscious function and general intelligence in humans and machines","created":"2022-03-24","cited_by_count":16,"area":null},{"id":"2306.01424","title":"Partial Counterfactual Identification of Continuous Outcomes with a Curvature Sensitivity Model","created":"2023-06-02","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":"2109.06093","title":"Direct Advantage Estimation","created":"2021-09-13","cited_by_count":11,"area":null},{"id":"2406.03234","title":"Fine-Grained Causal Dynamics Learning with Quantization for Improving Robustness in Reinforcement Learning","created":"2024-06-05","cited_by_count":11,"area":"deeprl"},{"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":"2305.10865","title":"Semantically Aligned Task Decomposition in Multi-Agent Reinforcement Learning","created":"2023-05-18","cited_by_count":8,"area":"agents"},{"id":"2402.12874","title":"Skill or Luck? Return Decomposition via Advantage Functions","created":"2024-02-20","cited_by_count":8,"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":"2310.04706","title":"Offline Imitation Learning with Variational Counterfactual Reasoning","created":"2023-10-07","cited_by_count":7,"area":"offlinerl"},{"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":"2602.07595","title":"TeleBoost: A Systematic Alignment Framework for High-Fidelity, Controllable, and Robust Video Generation","created":"2026-02-07","cited_by_count":7,"area":null},{"id":"2602.09331","title":"Beyond Uniform Credit: Causal Credit Assignment for Policy Optimization","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2108.02096","title":"Policy Gradients Incorporating the Future","created":"2021-08-04","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":"2412.06531","title":"Unraveling the Complexity of Memory in RL Agents: an Approach for Classification and Evaluation","created":"2024-12-09","cited_by_count":5,"area":"deeprl"},{"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":"2506.05188","title":"Counterfactual reasoning: an analysis of in-context emergence","created":"2025-06-05","cited_by_count":4,"area":"lr"},{"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":"2102.04999","title":"Adaptive Pairwise Weights for Temporal Credit Assignment","created":"2021-02-09","cited_by_count":2,"area":null},{"id":"2502.04809","title":"Humans Coexist, So Must Embodied Artificial Agents","created":"2025-02-07","cited_by_count":2,"area":null},{"id":"2510.15456","title":"Expediting Reinforcement Learning by Incorporating Knowledge About Temporal Causality in the Environment","created":"2025-10-17","cited_by_count":2,"area":"deeprl"},{"id":"2608.22092","title":"Counterfactual Quotient Models: Learning What Actions Change, Not What the World Does","created":"2026-08-22","cited_by_count":2,"area":null},{"id":"2505.09114","title":"Beyond the Known: Decision Making with Counterfactual Reasoning Decision Transformer","created":"2025-05-14","cited_by_count":1,"area":"offlinerl"},{"id":"2605.04811","title":"Tree-based Credit Assignment for Multi-Agent Memory System","created":"2026-05-06","cited_by_count":1,"area":"agents"},{"id":"2608.24588","title":"IAPO: Influence-Aware Policy Optimization for Credit Assignment in Multi-Turn Service Agents","created":"2026-08-25","cited_by_count":1,"area":"agents"},{"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":"2202.09489","title":"Shaping Advice in Deep Reinforcement Learning","created":"2022-02-19","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":"2502.06398","title":"Learning Counterfactual Outcomes Under Rank Preservation","created":"2025-02-10","cited_by_count":0,"area":null},{"id":"2509.16027","title":"What is a good matching of probability measures? A counterfactual lens on transport maps","created":"2025-09-19","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":"2512.09368","title":"CFLight: Enhancing Safety with Traffic Signal Control through Counterfactual Learning","created":"2025-12-10","cited_by_count":0,"area":"deeprl"},{"id":"2512.14726","title":"Quantum Decision Transformers (QDT): Synergistic Entanglement and Interference for Offline Reinforcement Learning","created":"2025-12-09","cited_by_count":0,"area":"offlinerl"},{"id":"2605.14004","title":"Conditional Attribute Estimation with Autoregressive Sequence Models","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2607.16999","title":"Counterfactual Shapley Credit Assignment","created":"2026-07-18","cited_by_count":0,"area":"deeprl"},{"id":"2608.29256","title":"Sense Once, Serve Many: Common-Trace Factorized Constrained PPO for Online Sensing-Session Consolidation in Multi-Tenant ISAC Networks","created":"2026-08-29","cited_by_count":0,"area":"deeprl"},{"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":"2609.33875","title":"Counterfactual Rollout Replay: Forkable Environments as Free Process Rewards for Software Engineering Agents","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.34177","title":"ReplayLens: Auditing Agents' Use of Outcomes","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.36058","title":"ABC: Advantage-Based Control Variates for Reinforcement Learning with Verifiable Rewards","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.37930","title":"Learning What to Remember: Long-horizon Counterfactual Memory Optimization","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.02330","title":"Choosing Before Acting: Comparative Value Estimation for Long-Horizon Tool-Use Agents","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"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"},{"id":"2610.14186","title":"Visualizing the World Model in an Agent's Value Function","created":"2026-10-09","cited_by_count":0,"area":"wm"},{"id":"2610.20497","title":"Hindsight-Privileged RLVR: Single-Rollout Token Credit Without Group Sampling","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}