{"total":15,"rows":[{"id":"2206.07568","title":"Contrastive Learning as Goal-Conditioned Reinforcement Learning","created":"2022-06-15","cited_by_count":253,"area":null},{"id":"2107.07002","title":"The Benchmark Lottery","created":"2021-07-14","cited_by_count":136,"area":null},{"id":"2203.15955","title":"Investigating the Properties of Neural Network Representations in Reinforcement Learning","created":"2022-03-30","cited_by_count":24,"area":null},{"id":"2202.06828","title":"On the Convergence of SARSA with Linear Function Approximation","created":"2022-02-14","cited_by_count":15,"area":null},{"id":"2212.14849","title":"Symbolic Visual Reinforcement Learning: A Scalable Framework with Object-Level Abstraction and Differentiable Expression Search","created":"2022-12-30","cited_by_count":9,"area":null},{"id":"2102.04881","title":"Measuring Progress in Deep Reinforcement Learning Sample Efficiency","created":"2021-02-09","cited_by_count":8,"area":null},{"id":"2202.03597","title":"Local Explanations for Reinforcement Learning","created":"2022-02-08","cited_by_count":5,"area":null},{"id":"2210.11262","title":"RMBench: Benchmarking Deep Reinforcement Learning for Robotic Manipulator Control","created":"2022-10-20","cited_by_count":5,"area":null},{"id":"2211.07805","title":"Agent-State Construction with Auxiliary Inputs","created":"2022-11-15","cited_by_count":3,"area":null},{"id":"2203.03078","title":"Fast and Data Efficient Reinforcement Learning from Pixels via Non-Parametric Value Approximation","created":"2022-03-07","cited_by_count":2,"area":null},{"id":"2109.03202","title":"On the impact of MDP design for Reinforcement Learning agents in Resource Management","created":"2021-09-07","cited_by_count":1,"area":null},{"id":"2109.15310","title":"Is Policy Learning Overrated?: Width-Based Planning and Active Learning for Atari","created":"2021-09-30","cited_by_count":1,"area":null},{"id":"2106.12151","title":"Width-based Lookaheads with Learnt Base Policies and Heuristics Over the Atari-2600 Benchmark","created":"2021-06-23","cited_by_count":0,"area":null},{"id":"2111.06907","title":"Improving Experience Replay through Modeling of Similar Transitions' Sets","created":"2021-11-12","cited_by_count":0,"area":null},{"id":"2505.00186","title":"Neuroevolution of Self-Attention Over Proto-Objects","created":"2025-04-30","cited_by_count":0,"area":null}],"next_cursor":null}