{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/sample-efficient-actor-critic-with-experience","title":"Sample Efficient Actor-Critic with Experience Replay","arxiv_id":"1611.01224","date":"2016-11-03","proceeding":null,"authors":["Ziyu Wang","Victor Bapst","Nicolas Heess","Volodymyr Mnih","Remi Munos","Koray Kavukcuoglu","Nando de Freitas"],"abstract":"This paper presents an actor-critic deep reinforcement learning agent with\nexperience replay that is stable, sample efficient, and performs remarkably\nwell on challenging environments, including the discrete 57-game Atari domain\nand several continuous control problems. To achieve this, the paper introduces\nseveral innovations, including truncated importance sampling with bias\ncorrection, stochastic dueling network architectures, and a new trust region\npolicy optimization method.","url_abs":"http://arxiv.org/abs/1611.01224v2","url_pdf":"http://arxiv.org/pdf/1611.01224v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"sample-efficient-actor-critic-with-experience","repo_url":"https://github.com/Kaixhin/ACER","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"sample-efficient-actor-critic-with-experience","repo_url":"https://github.com/PaulCharnay/Projet_AIF","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"sample-efficient-actor-critic-with-experience","repo_url":"https://github.com/chainer/chainerrl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"sample-efficient-actor-critic-with-experience","repo_url":"https://github.com/dchetelat/acer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"sample-efficient-actor-critic-with-experience","repo_url":"https://github.com/neilsgp/RL-Algorithms","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"sample-efficient-actor-critic-with-experience","repo_url":"https://github.com/hill-a/stable-baselines","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"sample-efficient-actor-critic-with-experience","repo_url":"https://github.com/opendilab/DI-engine/blob/main/ding/policy/acer.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"continuous-control","task_name":"Continuous Control"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"continuous-control","task_name":"continuous-control"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"acer","method_name":"ACER"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"double-q-learning","method_name":"Double Q-learning"},{"method_slug":"dueling-network","method_name":"Dueling Network"},{"method_slug":"entropy-regularization","method_name":"Entropy Regularization"},{"method_slug":"experience-replay","method_name":"Experience Replay"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"retrace","method_name":"Retrace"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"stochastic-dueling-network","method_name":"Stochastic Dueling Network"},{"method_slug":"trpo","method_name":"TRPO"}],"datasets_introduced":[],"methods_introduced":[{"slug":"acer","name":"ACER","full_name":"ACER"},{"slug":"stochastic-dueling-network","name":"Stochastic Dueling Network","full_name":"Stochastic Dueling Network"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1611.01224","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.01224"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hill-a/stable-baselines","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Kaixhin/ACER","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dchetelat/acer","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chainer/chainerrl","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PaulCharnay/Projet_AIF","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/opendilab/DI-engine/blob/main/ding/policy/acer.py","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/neilsgp/RL-Algorithms","reach":{"status":"ok"}}],"summary":{"unverified":1},"by_repo_kind":{"listed":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"2e8b614bc68e34e4","entry":"callback","repo":"PaulCharnay/Projet_AIF","repo_kind":"listed","path":"train_a2c.py","file_url":"https://github.com/PaulCharnay/Projet_AIF/blob/HEAD/train_a2c.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2e8b614bc68e34e4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}