{"total":31,"rows":[{"id":"2412.08021","title":"Can a MISL Fly? Analysis and Ingredients for Mutual Information Skill Learning","created":"2024-12-11","cited_by_count":21,"area":"deeprl"},{"id":"2411.02623","title":"Learning to Assist Humans without Inferring Rewards","created":"2024-11-04","cited_by_count":13,"area":"deeprl"},{"id":"2402.07411","title":"Potential-Based Reward Shaping For Intrinsic Motivation","created":"2024-02-12","cited_by_count":12,"area":"deeprl"},{"id":"2501.16918","title":"On Rollouts in Model-Based Reinforcement Learning","created":"2025-01-28","cited_by_count":10,"area":"deeprl"},{"id":"2403.16369","title":"Learning Action-based Representations Using Invariance","created":"2024-03-25","cited_by_count":7,"area":"deeprl"},{"id":"2410.10834","title":"Focus On What Matters: Separated Models For Visual-Based RL Generalization","created":"2024-09-29","cited_by_count":6,"area":"deeprl"},{"id":"2410.09972","title":"Make the Pertinent Salient: Task-Relevant Reconstruction for Visual Control with Distractions","created":"2024-10-13","cited_by_count":5,"area":"deeprl"},{"id":"2502.10077","title":"Towards Empowerment Gain through Causal Structure Learning in Model-Based RL","created":"2025-02-14","cited_by_count":5,"area":"deeprl"},{"id":"2510.14129","title":"Demystifying the Mechanisms Behind Emergent Exploration in Goal-conditioned RL","created":"2025-10-15","cited_by_count":5,"area":"deeprl"},{"id":"2407.12185","title":"Satisficing Exploration for Deep Reinforcement Learning","created":"2024-07-16","cited_by_count":4,"area":"deeprl"},{"id":"2409.05358","title":"BAMDP Shaping: a Unified Framework for Intrinsic Motivation and Reward Shaping","created":"2024-09-09","cited_by_count":4,"area":"deeprl"},{"id":"2507.14748","title":"Skill Learning via Policy Diversity Yields Identifiable Representations for Reinforcement Learning","created":"2025-07-19","cited_by_count":4,"area":"deeprl"},{"id":"2410.12197","title":"Potential-Based Intrinsic Motivation: Preserving Optimality With Complex, Non-Markovian Shaping Rewards","created":"2024-10-16","cited_by_count":3,"area":"deeprl"},{"id":"2501.17842","title":"From Sparse to Dense: Toddler-inspired Reward Transition in Goal-Oriented Reinforcement Learning","created":"2025-01-29","cited_by_count":3,"area":"deeprl"},{"id":"2508.21101","title":"Beyond Prediction: Reinforcement Learning as the Defining Leap in Healthcare AI","created":"2025-08-28","cited_by_count":3,"area":"deeprl"},{"id":"2602.11399","title":"Can We Really Learn One Representation to Optimize All Rewards?","created":"2026-02-11","cited_by_count":3,"area":"deeprl"},{"id":"2401.09034","title":"UOEP: User-Oriented Exploration Policy for Enhancing Long-Term User Experiences in Recommender Systems","created":"2024-01-17","cited_by_count":2,"area":"deeprl"},{"id":"2502.15820","title":"Universal AI maximizes Variational Empowerment","created":"2025-02-20","cited_by_count":2,"area":"deeprl"},{"id":"2510.05996","title":"Information-Theoretic Policy Pre-Training with Empowerment","created":"2025-10-07","cited_by_count":2,"area":"deeprl"},{"id":"2603.02008","title":"Temporal Representations for Exploration: Learning Complex Exploratory Behavior without Extrinsic Rewards","created":"2026-03-02","cited_by_count":2,"area":"deeprl"},{"id":"2603.18257","title":"Discovering What You Can Control: Interventional Boundary Discovery for Reinforcement Learning","created":"2026-03-18","cited_by_count":2,"area":"deeprl"},{"id":"2605.06145","title":"Unifying Goal-Conditioned RL and Unsupervised Skill Learning via Control-Maximization","created":"2026-05-07","cited_by_count":2,"area":"deeprl"},{"id":"2603.22273","title":"Decoupling Exploration and Policy Optimization: Uncertainty Guided Tree Search for Hard Exploration","created":"2026-03-23","cited_by_count":1,"area":"deeprl"},{"id":"2605.30656","title":"Learning to Perceive the World Through Control: Empowerment-Based Representation Learning","created":"2026-05-28","cited_by_count":1,"area":"deeprl"},{"id":"2502.00835","title":"CAIMAN: Causal Action Influence Detection for Sample-efficient Loco-manipulation","created":"2025-02-02","cited_by_count":0,"area":"deeprl"},{"id":"2505.08453","title":"Parameter Estimation using Reinforcement Learning Causal Curiosity: Limits and Challenges","created":"2025-05-13","cited_by_count":0,"area":"deeprl"},{"id":"2601.19810","title":"Unsupervised Learning of Efficient Exploration: Pre-training Adaptive Policies via Self-Imposed Goals","created":"2026-01-27","cited_by_count":0,"area":"deeprl"},{"id":"2603.01283","title":"The Informational Cost of Agency: A Bounded Measure of Interaction Efficiency for Deployed Reinforcement Learning","created":"2026-03-01","cited_by_count":0,"area":"deeprl"},{"id":"2605.12261","title":"Delay-Empowered Causal Hierarchical Reinforcement Learning","created":"2026-05-12","cited_by_count":0,"area":"deeprl"},{"id":"2609.10776","title":"A Bellman Optimality Equation for Plasticity","created":"2026-09-09","cited_by_count":0,"area":"deeprl"},{"id":"2610.02159","title":"When Do Intrinsic Rewards Lead to Exploration?","created":"2026-10-01","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}