{"total":78,"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":"2303.00957","title":"Preference Transformer: Modeling Human Preferences using Transformers for RL","created":"2023-03-02","cited_by_count":79,"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":"2111.13485","title":"Learning Long-Term Reward Redistribution via Randomized Return Decomposition","created":"2021-11-26","cited_by_count":33,"area":null},{"id":"2201.02373","title":"Mirror Learning: A Unifying Framework of Policy Optimisation","created":"2022-01-07","cited_by_count":31,"area":null},{"id":"2306.14884","title":"Learning to Modulate pre-trained Models in RL","created":"2023-06-26","cited_by_count":28,"area":null},{"id":"2102.12425","title":"Synthetic Returns for Long-Term Credit Assignment","created":"2021-02-24","cited_by_count":27,"area":null},{"id":"2106.11854","title":"Off-Policy Reinforcement Learning with Delayed Rewards","created":"2021-06-22","cited_by_count":25,"area":null},{"id":"2310.03301","title":"Learning Energy Decompositions for Partial Inference of GFlowNets","created":"2023-10-05","cited_by_count":24,"area":null},{"id":"2603.22293","title":"TIPS: Turn-Level Information-Potential Reward Shaping for Search-Augmented LLMs","created":"2026-03-11","cited_by_count":24,"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":"2211.15457","title":"Hypernetworks for Zero-shot Transfer in Reinforcement Learning","created":"2022-11-28","cited_by_count":19,"area":null},{"id":"2305.18427","title":"Interpretable Reward Redistribution in Reinforcement Learning: A Causal Approach","created":"2023-05-28","cited_by_count":19,"area":null},{"id":"2101.00240","title":"A Survey on Deep Reinforcement Learning for Audio-Based Applications","created":"2021-01-01","cited_by_count":17,"area":null},{"id":"2306.09312","title":"Semantic HELM: A Human-Readable Memory for Reinforcement Learning","created":"2023-06-15","cited_by_count":17,"area":null},{"id":"2402.00854","title":"SymbolicAI: A framework for logic-based approaches combining generative models and solvers","created":"2024-02-01","cited_by_count":16,"area":null},{"id":"2607.13988","title":"TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents","created":"2026-07-15","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":"2310.06794","title":"$f$-Policy Gradients: A General Framework for Goal Conditioned RL using $f$-Divergences","created":"2023-10-10","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":"2501.13075","title":"Evolution and The Knightian Blindspot of Machine Learning","created":"2025-01-22","cited_by_count":11,"area":null},{"id":"2502.15886","title":"A Close Look at Decomposition-based XAI-Methods for Transformer Language Models","created":"2025-02-21","cited_by_count":11,"area":null},{"id":"2201.04612","title":"Agent-Temporal Attention for Reward Redistribution in Episodic Multi-Agent Reinforcement Learning","created":"2022-01-12","cited_by_count":9,"area":null},{"id":"2203.11526","title":"Action Candidate Driven Clipped Double Q-learning for Discrete and Continuous Action Tasks","created":"2022-03-22","cited_by_count":9,"area":null},{"id":"2205.12532","title":"Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning","created":"2022-05-25","cited_by_count":9,"area":null},{"id":"2207.05742","title":"Reactive Exploration to Cope with Non-Stationarity in Lifelong Reinforcement Learning","created":"2022-07-12","cited_by_count":9,"area":null},{"id":"2308.07795","title":"Learning to Identify Critical States for Reinforcement Learning from Videos","created":"2023-08-15","cited_by_count":9,"area":null},{"id":"2111.05884","title":"Search in Imperfect Information Games","created":"2021-11-10","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":"2302.00237","title":"Bridging Physics-Informed Neural Networks with Reinforcement Learning: Hamilton-Jacobi-Bellman Proximal Policy Optimization (HJBPPO)","created":"2023-02-01","cited_by_count":7,"area":null},{"id":"2210.17540","title":"Agent-Time Attention for Sparse Rewards Multi-Agent Reinforcement Learning","created":"2022-10-31","cited_by_count":6,"area":null},{"id":"2306.03293","title":"Towards Fairness in Personalized Ads Using Impression Variance Aware Reinforcement Learning","created":"2023-06-05","cited_by_count":6,"area":null},{"id":"2312.11364","title":"Counting Reward Automata: Sample Efficient Reinforcement Learning Through the Exploitation of Reward Function Structure","created":"2023-12-18","cited_by_count":6,"area":null},{"id":"2606.00593","title":"SPADER: Step-wise Peer Advantage with Diversity-Aware Exploration Rewards for Multi-Answer Question Answering","created":"2026-05-30","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":"2209.03798","title":"ReX: A Framework for Incorporating Temporal Information in Model-Agnostic Local Explanation Techniques","created":"2022-09-08","cited_by_count":5,"area":null},{"id":"2304.07520","title":"STAS: Spatial-Temporal Return Decomposition for Multi-agent Reinforcement Learning","created":"2023-04-15","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":"2307.11897","title":"Hindsight-DICE: Stable Credit Assignment for Deep Reinforcement Learning","created":"2023-07-21","cited_by_count":4,"area":null},{"id":"2409.04744","title":"Reward Guidance for Reinforcement Learning Tasks Based on Large Language Models: The LMGT Framework","created":"2024-09-07","cited_by_count":4,"area":null},{"id":"2106.05332","title":"Reinforcement Learning for Industrial Control Network Cyber Security Orchestration","created":"2021-06-09","cited_by_count":3,"area":null},{"id":"2307.04098","title":"A User Study on Explainable Online Reinforcement Learning for Adaptive Systems","created":"2023-07-09","cited_by_count":3,"area":null},{"id":"2605.27788","title":"Knowing When to Ask: Segment-Level Credit Assignment for LLM Tool Use","created":"2026-05-27","cited_by_count":3,"area":null},{"id":"2607.22832","title":"MEMENTO: Memory-Guided Memetic Code-as-Policy Evolution","created":"2026-07-24","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":"2202.10464","title":"A Globally Convergent Evolutionary Strategy for Stochastic Constrained Optimization with Applications to Reinforcement Learning","created":"2022-02-21","cited_by_count":2,"area":null},{"id":"2303.13660","title":"Presenting Multiagent Challenges in Team Sports Analytics","created":"2023-03-23","cited_by_count":2,"area":null},{"id":"2306.16205","title":"Towards a Better Understanding of Learning with Multiagent Teams","created":"2023-06-28","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":"2411.09176","title":"Gazing at Rewards: Eye Movements as a Lens into Human and AI Decision-Making in Hybrid Visual Foraging","created":"2024-11-14","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":"2111.02445","title":"Autonomous Attack Mitigation for Industrial Control Systems","created":"2021-11-03","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":"2205.13718","title":"Off-Beat Multi-Agent Reinforcement Learning","created":"2022-05-27","cited_by_count":1,"area":null},{"id":"2301.09631","title":"Feature construction using explanations of individual predictions","created":"2023-01-23","cited_by_count":1,"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":"2505.20579","title":"The challenge of hidden gifts in multi-agent reinforcement learning","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2608.02694","title":"Crayotter: Learning Long-Horizon Video Editing Agents via Group-Relative Preference Backpropagation","created":"2026-08-03","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":"2102.11717","title":"Greedy-Step Off-Policy Reinforcement Learning","created":"2021-02-23","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":"2210.13545","title":"MEET: A Monte Carlo Exploration-Exploitation Trade-off for Buffer Sampling","created":"2022-10-24","cited_by_count":0,"area":null},{"id":"2211.10550","title":"Debiasing Meta-Gradient Reinforcement Learning by Learning the Outer Value Function","created":"2022-11-19","cited_by_count":0,"area":null},{"id":"2307.00758","title":"Structured Network Pruning by Measuring Filter-wise Interactions","created":"2023-07-03","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":"2504.11250","title":"A Rollout-Based Algorithm and Reward Function for Resource Allocation in Business Processes","created":"2025-04-15","cited_by_count":0,"area":null},{"id":"2509.12716","title":"Joint AoI and Handover Optimization in Space-Air-Ground Integrated Network","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2606.30442","title":"The FIL Hypothesis: Inductive Biases Help with Kernel Engineering","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2609.12890","title":"Large Distant Gradients Need Not Be Reliable: reliability-weighted credit assignment for long-horizon autoregressive forecasting","created":"2026-09-11","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},{"id":"2610.01128","title":"Grounding Large Language Models in DSGE Simulators for Policy Generation and Forecasting","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.03099","title":"Beyond Single Videos: Benchmarking and Active Evidence Seeking for E-Commerce Cross-Video Reasoning","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.03372","title":"SCAD: Structured Credit Assignment and Distillation for Long-Horizon Agents","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.16027","title":"Of Errors and Echoes: Responsibility-Aware Credit Assignment for Tool-Use Agents","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}