{"total":10,"rows":[{"id":"2310.19007","title":"Behavior Alignment via Reward Function Optimization","created":"2023-10-29","cited_by_count":16,"area":null},{"id":"2206.02126","title":"Learning Dynamics and Generalization in Reinforcement Learning","created":"2022-06-05","cited_by_count":14,"area":null},{"id":"2210.06041","title":"Reinforcement Learning with Automated Auxiliary Loss Search","created":"2022-10-12","cited_by_count":13,"area":null},{"id":"2310.01365","title":"Elephant Neural Networks: Born to Be a Continual Learner","created":"2023-10-02","cited_by_count":10,"area":null},{"id":"2205.10868","title":"Memory-efficient Reinforcement Learning with Value-based Knowledge Consolidation","created":"2022-05-22","cited_by_count":9,"area":null},{"id":"2102.07686","title":"Does the Adam Optimizer Exacerbate Catastrophic Forgetting?","created":"2021-02-15","cited_by_count":5,"area":null},{"id":"2505.13025","title":"LiBOG: Lifelong Learning for Black-Box Optimizer Generation","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2204.06550","title":"Improving generalization to new environments and removing catastrophic forgetting in Reinforcement Learning by using an eco-system of agents","created":"2022-04-13","cited_by_count":0,"area":null},{"id":"2212.05377","title":"Generalization Through the Lens of Learning Dynamics","created":"2022-12-11","cited_by_count":0,"area":null},{"id":"2212.06451","title":"Improving generalization in reinforcement learning through forked agents","created":"2022-12-13","cited_by_count":0,"area":null}],"next_cursor":null}