{"total":35,"rows":[{"id":"2107.12808","title":"Open-Ended Learning Leads to Generally Capable Agents","created":"2021-07-27","cited_by_count":182,"area":null},{"id":"2112.13112","title":"A Survey on Interpretable Reinforcement Learning","created":"2021-12-24","cited_by_count":73,"area":null},{"id":"2111.00876","title":"On the Expressivity of Markov Reward","created":"2021-11-01","cited_by_count":71,"area":null},{"id":"2207.00429","title":"Modular Lifelong Reinforcement Learning via Neural Composition","created":"2022-07-01","cited_by_count":40,"area":null},{"id":"2205.13521","title":"Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimality","created":"2022-05-26","cited_by_count":37,"area":null},{"id":"2207.07730","title":"How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition","created":"2022-07-15","cited_by_count":27,"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":"2207.04136","title":"CompoSuite: A Compositional Reinforcement Learning Benchmark","created":"2022-07-08","cited_by_count":21,"area":null},{"id":"2310.03718","title":"Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learning","created":"2023-10-05","cited_by_count":18,"area":null},{"id":"2105.04962","title":"Composable Energy Policies for Reactive Motion Generation and Reinforcement Learning","created":"2021-05-11","cited_by_count":16,"area":null},{"id":"2308.09175","title":"Diversifying AI: Towards Creative Chess with AlphaZero","created":"2023-08-17","cited_by_count":15,"area":null},{"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":"2205.12532","title":"Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning","created":"2022-05-25","cited_by_count":9,"area":null},{"id":"2212.01174","title":"Utilizing Prior Solutions for Reward Shaping and Composition in Entropy-Regularized Reinforcement Learning","created":"2022-12-02","cited_by_count":8,"area":null},{"id":"2310.00435","title":"Consistent Aggregation of Objectives with Diverse Time Preferences Requires Non-Markovian Rewards","created":"2023-09-30","cited_by_count":8,"area":null},{"id":"2106.15380","title":"Globally Optimal Hierarchical Reinforcement Learning for Linearly-Solvable Markov Decision Processes","created":"2021-06-29","cited_by_count":6,"area":null},{"id":"2202.09064","title":"Can Interpretable Reinforcement Learning Manage Prosperity Your Way?","created":"2022-02-18","cited_by_count":6,"area":null},{"id":"2111.09475","title":"Lifelong Reinforcement Learning with Temporal Logic Formulas and Reward Machines","created":"2021-11-18","cited_by_count":5,"area":null},{"id":"2208.13687","title":"Categorical semantics of compositional reinforcement learning","created":"2022-08-29","cited_by_count":5,"area":null},{"id":"2304.12090","title":"Reinforcement Learning with Knowledge Representation and Reasoning: A Brief Survey","created":"2023-04-24","cited_by_count":5,"area":null},{"id":"2205.15752","title":"Hierarchies of Reward Machines","created":"2022-05-31","cited_by_count":4,"area":null},{"id":"2302.01561","title":"Hierarchically Composing Level Generators for the Creation of Complex Structures","created":"2023-02-03","cited_by_count":4,"area":null},{"id":"2110.04647","title":"Learning to Follow Language Instructions with Compositional Policies","created":"2021-10-09","cited_by_count":3,"area":null},{"id":"2211.06665","title":"A Survey on Explainable Reinforcement Learning: Concepts, Algorithms, Challenges","created":"2022-11-12","cited_by_count":3,"area":null},{"id":"2303.02557","title":"Bounding the Optimal Value Function in Compositional Reinforcement Learning","created":"2023-03-05","cited_by_count":3,"area":null},{"id":"2205.08827","title":"World Value Functions: Knowledge Representation for Multitask Reinforcement Learning","created":"2022-05-18","cited_by_count":2,"area":null},{"id":"2211.05361","title":"Safety-Constrained Policy Transfer with Successor Features","created":"2022-11-10","cited_by_count":2,"area":null},{"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":"2204.09218","title":"Reinforcement Learning with Intrinsic Affinity for Personalized Prosperity Management","created":"2022-04-20","cited_by_count":1,"area":null},{"id":"2206.11940","title":"World Value Functions: Knowledge Representation for Learning and Planning","created":"2022-06-23","cited_by_count":1,"area":null},{"id":"2302.09676","title":"Leveraging Prior Knowledge in Reinforcement Learning via Double-Sided Bounds on the Value Function","created":"2023-02-19","cited_by_count":0,"area":null},{"id":"2306.17033","title":"Safety-Aware Task Composition for Discrete and Continuous Reinforcement Learning","created":"2023-06-29","cited_by_count":0,"area":null},{"id":"2501.12539","title":"Compositional Instruction Following with Language Models and Reinforcement Learning","created":"2025-01-21","cited_by_count":0,"area":null},{"id":"2512.18633","title":"ARC: Leveraging Compositional Representations for Cross-Problem Learning on VRPs","created":"2025-12-21","cited_by_count":0,"area":null},{"id":"2609.19448","title":"The syntax and semantics of goals","created":"2026-09-16","cited_by_count":0,"area":null}],"next_cursor":null}