{"total":13,"rows":[{"id":"2103.04047","title":"Reinforcement Learning, Bit by Bit","created":"2021-03-06","cited_by_count":59,"area":null},{"id":"2204.05080","title":"Semantic Exploration from Language Abstractions and Pretrained Representations","created":"2022-04-08","cited_by_count":51,"area":null},{"id":"2107.14226","title":"Learning more skills through optimistic exploration","created":"2021-07-29","cited_by_count":38,"area":null},{"id":"2201.01666","title":"Sample Efficient Deep Reinforcement Learning via Uncertainty Estimation","created":"2022-01-05","cited_by_count":27,"area":null},{"id":"2108.11811","title":"When should agents explore?","created":"2021-08-26","cited_by_count":20,"area":null},{"id":"2206.02072","title":"Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning","created":"2022-06-04","cited_by_count":19,"area":null},{"id":"2305.00477","title":"Posterior Sampling for Deep Reinforcement Learning","created":"2023-04-30","cited_by_count":16,"area":null},{"id":"2306.07124","title":"Diverse Projection Ensembles for Distributional Reinforcement Learning","created":"2023-06-12","cited_by_count":8,"area":null},{"id":"2112.04153","title":"Model-Value Inconsistency as a Signal for Epistemic Uncertainty","created":"2021-12-08","cited_by_count":6,"area":null},{"id":"2212.10765","title":"Reward Bonuses with Gain Scheduling Inspired by Iterative Deepening Search","created":"2022-12-21","cited_by_count":5,"area":null},{"id":"2304.09547","title":"Graph Exploration for Effective Multi-agent Q-Learning","created":"2023-04-19","cited_by_count":1,"area":null},{"id":"2305.01322","title":"An Autonomous Non-monolithic Agent with Multi-mode Exploration based on Options Framework","created":"2023-05-02","cited_by_count":0,"area":null},{"id":"2512.15948","title":"Subjective functions","created":"2025-12-17","cited_by_count":0,"area":null}],"next_cursor":null}