{"total":103,"rows":[{"id":"2103.09568","title":"A Practical Guide to Multi-Objective Reinforcement Learning and Planning","created":"2021-03-17","cited_by_count":256,"area":null},{"id":"2206.07568","title":"Contrastive Learning as Goal-Conditioned Reinforcement Learning","created":"2022-06-15","cited_by_count":253,"area":null},{"id":"2103.07945","title":"Learning One Representation to Optimize All Rewards","created":"2021-03-14","cited_by_count":115,"area":null},{"id":"2108.13956","title":"APS: Active Pretraining with Successor Features","created":"2021-08-31","cited_by_count":112,"area":null},{"id":"2402.15567","title":"Foundation Policies with Hilbert Representations","created":"2024-02-23","cited_by_count":94,"area":"deeprl"},{"id":"2209.14935","title":"Does Zero-Shot Reinforcement Learning Exist?","created":"2022-09-29","cited_by_count":83,"area":null},{"id":"2101.07123","title":"Learning Successor States and Goal-Dependent Values: A Mathematical Viewpoint","created":"2021-01-18","cited_by_count":70,"area":null},{"id":"2304.04782","title":"Reinforcement Learning from Passive Data via Latent Intentions","created":"2023-04-10","cited_by_count":68,"area":null},{"id":"2106.13105","title":"The Option Keyboard: Combining Skills in Reinforcement Learning","created":"2021-06-24","cited_by_count":67,"area":null},{"id":"2110.05740","title":"Temporal Abstraction in Reinforcement Learning with the Successor Representation","created":"2021-10-12","cited_by_count":54,"area":null},{"id":"2301.07784","title":"Sample-Efficient Multi-Objective Learning via Generalized Policy Improvement Prioritization","created":"2023-01-18","cited_by_count":48,"area":null},{"id":"2102.10960","title":"Return-Based Contrastive Representation Learning for Reinforcement Learning","created":"2021-02-22","cited_by_count":36,"area":null},{"id":"2305.18882","title":"What is Essential for Unseen Goal Generalization of Offline Goal-conditioned RL?","created":"2023-05-30","cited_by_count":36,"area":"offlinerl"},{"id":"2402.17135","title":"Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings","created":"2024-02-27","cited_by_count":31,"area":"deeprl"},{"id":"2503.09817","title":"Temporal Difference Flows","created":"2025-03-12","cited_by_count":24,"area":null},{"id":"2102.12560","title":"PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning","created":"2021-02-24","cited_by_count":23,"area":null},{"id":"2111.09858","title":"Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement Learning","created":"2021-11-18","cited_by_count":23,"area":null},{"id":"2306.14808","title":"Maximum State Entropy Exploration using Predecessor and Successor Representations","created":"2023-06-26","cited_by_count":23,"area":null},{"id":"2206.11326","title":"Optimistic Linear Support and Successor Features as a Basis for Optimal Policy Transfer","created":"2022-06-22","cited_by_count":22,"area":null},{"id":"2102.13515","title":"Beyond Fine-Tuning: Transferring Behavior in Reinforcement Learning","created":"2021-02-24","cited_by_count":21,"area":null},{"id":"2309.15178","title":"Zero-Shot Reinforcement Learning from Low Quality Data","created":"2023-09-26","cited_by_count":21,"area":null},{"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":"2504.07896","title":"Fast Adaptation with Behavioral Foundation Models","created":"2025-04-10","cited_by_count":21,"area":"deeprl"},{"id":"2108.11811","title":"When should agents explore?","created":"2021-08-26","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":"2401.17173","title":"Zero-Shot Reinforcement Learning via Function Encoders","created":"2024-01-30","cited_by_count":18,"area":"deeprl"},{"id":"2402.08530","title":"A Distributional Analogue to the Successor Representation","created":"2024-02-13","cited_by_count":17,"area":"deeprl"},{"id":"2112.15025","title":"Constructing a Good Behavior Basis for Transfer using Generalized Policy Updates","created":"2021-12-30","cited_by_count":14,"area":null},{"id":"2206.08736","title":"Generalised Policy Improvement with Geometric Policy Composition","created":"2022-06-17","cited_by_count":13,"area":null},{"id":"2208.08133","title":"Metric Residual Networks for Sample Efficient Goal-Conditioned Reinforcement Learning","created":"2022-08-17","cited_by_count":13,"area":null},{"id":"2403.09930","title":"Quality-Diversity Actor-Critic: Learning High-Performing and Diverse Behaviors via Value and Successor Features Critics","created":"2024-03-15","cited_by_count":13,"area":"deeprl"},{"id":"2105.14127","title":"Risk-Aware Transfer in Reinforcement Learning using Successor Features","created":"2021-05-28","cited_by_count":12,"area":null},{"id":"2310.15940","title":"Combining Behaviors with the Successor Features Keyboard","created":"2023-10-24","cited_by_count":12,"area":null},{"id":"2412.04368","title":"Finer Behavioral Foundation Models via Auto-Regressive Features and Advantage Weighting","created":"2024-12-05","cited_by_count":12,"area":"offlinerl"},{"id":"2410.22133","title":"Learning Successor Features the Simple Way","created":"2024-10-29","cited_by_count":10,"area":"deeprl"},{"id":"2411.07007","title":"Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching","created":"2024-11-11","cited_by_count":10,"area":"offlinerl"},{"id":"2104.11707","title":"DisCo RL: Distribution-Conditioned Reinforcement Learning for General-Purpose Policies","created":"2021-04-23","cited_by_count":9,"area":null},{"id":"2202.11133","title":"Continual Auxiliary Task Learning","created":"2022-02-22","cited_by_count":9,"area":null},{"id":"2204.13695","title":"Bilinear value networks","created":"2022-04-28","cited_by_count":9,"area":null},{"id":"2506.08902","title":"Intention-Conditioned Flow Occupancy Models","created":"2025-06-10","cited_by_count":9,"area":null},{"id":"2402.13037","title":"Align Your Intents: Offline Imitation Learning via Optimal Transport","created":"2024-02-20","cited_by_count":8,"area":"offlinerl"},{"id":"2403.06328","title":"Distributional Successor Features Enable Zero-Shot Policy Optimization","created":"2024-03-10","cited_by_count":8,"area":null},{"id":"2503.17338","title":"Capturing Individual Human Preferences with Reward Features","created":"2025-03-21","cited_by_count":8,"area":"alignment"},{"id":"2505.13150","title":"Zero-Shot Adaptation of Behavioral Foundation Models to Unseen Dynamics","created":"2025-05-19","cited_by_count":8,"area":null},{"id":"2106.03853","title":"DisTop: Discovering a Topological representation to learn diverse and rewarding skills","created":"2021-06-06","cited_by_count":7,"area":null},{"id":"2209.15205","title":"ASPiRe:Adaptive Skill Priors for Reinforcement Learning","created":"2022-09-30","cited_by_count":7,"area":null},{"id":"2301.12305","title":"Composing Task Knowledge with Modular Successor Feature Approximators","created":"2023-01-28","cited_by_count":7,"area":null},{"id":"2510.15382","title":"Towards Robust Zero-Shot Reinforcement Learning","created":"2025-10-17","cited_by_count":7,"area":"deeprl"},{"id":"2602.19634","title":"Compositional Planning with Jumpy World Models","created":"2026-02-23","cited_by_count":7,"area":"wm"},{"id":"2608.09853","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","created":"2026-08-10","cited_by_count":7,"area":"alignment"},{"id":"2103.02650","title":"Successor Feature Sets: Generalizing Successor Representations Across Policies","created":"2021-03-03","cited_by_count":6,"area":null},{"id":"2110.15701","title":"Successor Feature Representations","created":"2021-10-29","cited_by_count":6,"area":null},{"id":"2206.13901","title":"Value Function Decomposition for Iterative Design of Reinforcement Learning Agents","created":"2022-06-24","cited_by_count":6,"area":null},{"id":"2506.15446","title":"Zero-Shot Reinforcement Learning Under Partial Observability","created":"2025-06-18","cited_by_count":6,"area":"deeprl"},{"id":"2104.02981","title":"Reinforcement Learning with a Disentangled Universal Value Function for Item Recommendation","created":"2021-04-07","cited_by_count":4,"area":"wm"},{"id":"2208.04919","title":"Basis for Intentions: Efficient Inverse Reinforcement Learning using Past Experience","created":"2022-08-09","cited_by_count":4,"area":"offlinerl"},{"id":"2402.06590","title":"Predictive representations: building blocks of intelligence","created":"2024-02-09","cited_by_count":4,"area":null},{"id":"2505.16217","title":"Reward-Aware Proto-Representations in Reinforcement Learning","created":"2025-05-22","cited_by_count":4,"area":"deeprl"},{"id":"2111.03110","title":"Successor Feature Neural Episodic Control","created":"2021-11-04","cited_by_count":3,"area":null},{"id":"2501.02330","title":"SR-Reward: Taking The Path More Traveled","created":"2025-01-04","cited_by_count":3,"area":"offlinerl"},{"id":"2502.10790","title":"Which Features are Best for Successor Features?","created":"2025-02-15","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":"2311.04921","title":"Successor Features for Efficient Multisubject Controlled Text Generation","created":"2023-11-03","cited_by_count":2,"area":null},{"id":"2404.03997","title":"Demonstration Guided Multi-Objective Reinforcement Learning","created":"2024-04-05","cited_by_count":2,"area":"deeprl"},{"id":"2406.10127","title":"Exploration by Learning Diverse Skills through Successor State Measures","created":"2024-06-14","cited_by_count":2,"area":null},{"id":"2407.13887","title":"Learning Goal-Conditioned Representations for Language Reward Models","created":"2024-07-18","cited_by_count":2,"area":"alignment"},{"id":"2505.00787","title":"Constructing an Optimal Behavior Basis for the Option Keyboard","created":"2025-05-01","cited_by_count":2,"area":"deeprl"},{"id":"2507.05561","title":"Preemptive Solving of Future Problems: Multitask Preplay in Humans and Machines","created":"2025-07-08","cited_by_count":2,"area":null},{"id":"2602.01962","title":"Zero-Shot Off-Policy Learning","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2604.24532","title":"A Reward-Free Viewpoint on Multi-Objective Reinforcement Learning","created":"2026-04-27","cited_by_count":2,"area":"deeprl"},{"id":"2201.00236","title":"Operator Deep Q-Learning: Zero-Shot Reward Transferring in Reinforcement Learning","created":"2022-01-01","cited_by_count":1,"area":null},{"id":"2205.10175","title":"Task Relabelling for Multi-task Transfer using Successor Features","created":"2022-05-20","cited_by_count":1,"area":null},{"id":"2305.17623","title":"On the Value of Myopic Behavior in Policy Reuse","created":"2023-05-28","cited_by_count":1,"area":null},{"id":"2405.02569","title":"Decoupling Exploration and Exploitation for Unsupervised Pre-training with Successor Features","created":"2024-05-04","cited_by_count":1,"area":null},{"id":"2506.01623","title":"MAGIK: Mapping to Analogous Goals via Imagination-enabled Knowledge Transfer","created":"2025-06-02","cited_by_count":1,"area":"lr"},{"id":"2506.15190","title":"Learning Task-Agnostic Motifs to Capture the Continuous Nature of Animal Behavior","created":"2025-06-18","cited_by_count":1,"area":null},{"id":"2510.20542","title":"A Unified Framework for Zero-Shot Reinforcement Learning","created":"2025-10-23","cited_by_count":1,"area":"deeprl"},{"id":"2601.21548","title":"Training slow silicon neurons to control extremely fast robots with spiking reinforcement learning","created":"2026-01-29","cited_by_count":1,"area":"deeprl"},{"id":"2602.07730","title":"The Laplacian Keyboard: Beyond the Linear Span","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2603.05066","title":"Reward-Conditioned Reinforcement Learning","created":"2026-03-05","cited_by_count":1,"area":"alignment"},{"id":"2603.25464","title":"Maximum Entropy Behavior Exploration for Sim2Real Zero-Shot Reinforcement Learning","created":"2026-03-26","cited_by_count":1,"area":"deeprl"},{"id":"2604.25496","title":"Improving Zero-Shot Offline RL via Behavioral Task Sampling","created":"2026-04-28","cited_by_count":1,"area":"offlinerl"},{"id":"2605.26357","title":"Balancing Plasticity and Stability with Fast and Slow Successor Features","created":"2026-05-25","cited_by_count":1,"area":"deeprl"},{"id":"2606.01123","title":"From Reward-Free Representations to Preferences: Rethinking Offline Preference-Based Reinforcement Learning","created":"2026-05-31","cited_by_count":1,"area":"alignment"},{"id":"2606.21173","title":"Inverting the Bellman Equation: From $Q$-Values to World Models","created":"2026-06-19","cited_by_count":1,"area":"wm"},{"id":"2606.29980","title":"Exploration and Online Transfer with Behavioral Foundation Models","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2112.08369","title":"Feature-Attending Recurrent Modules for Generalization in Reinforcement Learning","created":"2021-12-15","cited_by_count":0,"area":null},{"id":"2201.01836","title":"A Generalized Bootstrap Target for Value-Learning, Efficiently Combining Value and Feature Predictions","created":"2022-01-05","cited_by_count":0,"area":null},{"id":"2212.09033","title":"Planning Immediate Landmarks of Targets for Model-Free Skill Transfer across Agents","created":"2022-12-18","cited_by_count":0,"area":null},{"id":"2305.14377","title":"Unsupervised Discovery of Continuous Skills on a Sphere","created":"2023-05-21","cited_by_count":0,"area":null},{"id":"2409.04641","title":"Stacked Universal Successor Feature Approximators for Safety in Reinforcement Learning","created":"2024-09-06","cited_by_count":0,"area":"deeprl"},{"id":"2502.10792","title":"Tackling the Zero-Shot Reinforcement Learning Loss Directly","created":"2025-02-15","cited_by_count":0,"area":"deeprl"},{"id":"2508.07722","title":"Robust Remote Reinforcement Learning over Unreliable Communication Channels using Homomorphic State Encoding","created":"2025-08-11","cited_by_count":0,"area":"deeprl"},{"id":"2509.22310","title":"Adaptive Policy Backbone via Shared Network","created":"2025-09-26","cited_by_count":0,"area":"deeprl"},{"id":"2602.00403","title":"DROGO: Default Representation Objective via Graph Optimization in Reinforcement Learning","created":"2026-01-30","cited_by_count":0,"area":"deeprl"},{"id":"2605.17017","title":"When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited","created":"2026-05-16","cited_by_count":0,"area":"offlinerl"},{"id":"2605.23551","title":"Goal-Conditioned Agents that Learn Everything All at Once","created":"2026-05-22","cited_by_count":0,"area":"deeprl"},{"id":"2606.04053","title":"A Goal-Set Characterization of Task Composition in the Boolean Task Algebra","created":"2026-06-02","cited_by_count":0,"area":"deeprl"},{"id":"2607.09298","title":"Risk-Aware General-Utility Markov Decision Processes","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2607.27574","title":"Policy Gradient Steering: Interventions from Behavioral Objectives","created":"2026-07-30","cited_by_count":0,"area":"mechinterp"}],"next_cursor":"100"}