{"work":{"id":"e424bccd-03ff-4986-ab5b-893e9ecd7977","openalex_id":null,"doi":null,"arxiv_id":"1611.01224","raw_key":null,"title":"Sample Efficient Actor-Critic with Experience Replay","authors":null,"authors_text":"Sample efficient actor-critic with experience replay , author=","year":2016,"venue":"cs.LG","abstract":"This paper presents an actor-critic deep reinforcement learning agent with experience replay that is stable, sample efficient, and performs remarkably well on challenging environments, including the discrete 57-game Atari domain and several continuous control problems. To achieve this, the paper introduces several innovations, including truncated importance sampling with bias correction, stochastic dueling network architectures, and a new trust region policy optimization method.","external_url":"https://arxiv.org/abs/1611.01224","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-25T17:46:05.937418+00:00","pith_arxiv_id":"1611.01224","created_at":"2026-05-10T11:30:18.799748+00:00","updated_at":"2026-06-05T21:23:00.469572+00:00","title_quality_ok":true,"display_title":"Sample Efficient Actor-Critic with Experience Replay","render_title":"Sample Efficient Actor-Critic with Experience Replay"},"hub":{"state":{"work_id":"e424bccd-03ff-4986-ab5b-893e9ecd7977","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":12,"external_cited_by_count":null,"distinct_field_count":4,"first_pith_cited_at":"2019-06-24T05:37:58+00:00","last_pith_cited_at":"2026-05-20T10:38:08+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-06-08T09:32:54.696898+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":1}],"polarity_counts":[{"context_polarity":"background","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}