{"total":7,"rows":[{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807,"area":null},{"id":"2207.00986","title":"Stabilizing Off-Policy Deep Reinforcement Learning from Pixels","created":"2022-07-03","cited_by_count":32,"area":null},{"id":"2206.00730","title":"The Phenomenon of Policy Churn","created":"2022-06-01","cited_by_count":28,"area":null},{"id":"2209.07550","title":"Human-level Atari 200x faster","created":"2022-09-15","cited_by_count":28,"area":null},{"id":"2108.11811","title":"When should agents explore?","created":"2021-08-26","cited_by_count":20,"area":null},{"id":"2306.00249","title":"BetaZero: Belief-State Planning for Long-Horizon POMDPs using Learned Approximations","created":"2023-05-31","cited_by_count":14,"area":null},{"id":"2212.14214","title":"Backward Curriculum Reinforcement Learning","created":"2022-12-29","cited_by_count":0,"area":null}],"next_cursor":null}