{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/advantage-weighted-regression-simple-and","title":"Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning","arxiv_id":"1910.00177","date":"2019-10-01","proceeding":null,"authors":["Xue Bin Peng","Aviral Kumar","Grace Zhang","Sergey Levine"],"abstract":"In this paper, we aim to develop a simple and scalable reinforcement learning algorithm that uses standard supervised learning methods as subroutines. Our goal is an algorithm that utilizes only simple and convergent maximum likelihood loss functions, while also being able to leverage off-policy data. Our proposed approach, which we refer to as advantage-weighted regression (AWR), consists of two standard supervised learning steps: one to regress onto target values for a value function, and another to regress onto weighted target actions for the policy. The method is simple and general, can accommodate continuous and discrete actions, and can be implemented in just a few lines of code on top of standard supervised learning methods. We provide a theoretical motivation for AWR and analyze its properties when incorporating off-policy data from experience replay. We evaluate AWR on a suite of standard OpenAI Gym benchmark tasks, and show that it achieves competitive performance compared to a number of well-established state-of-the-art RL algorithms. AWR is also able to acquire more effective policies than most off-policy algorithms when learning from purely static datasets with no additional environmental interactions. Furthermore, we demonstrate our algorithm on challenging continuous control tasks with highly complex simulated characters.","url_abs":"https://arxiv.org/abs/1910.00177v3","url_pdf":"https://arxiv.org/pdf/1910.00177v3.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":"advantage-weighted-regression-simple-and","repo_url":"https://github.com/NitinVishalKulkarni/OfflineReinforcementLearning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"advantage-weighted-regression-simple-and","repo_url":"https://github.com/fomorians-oss/awr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"advantage-weighted-regression-simple-and","repo_url":"https://github.com/google/trax","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"advantage-weighted-regression-simple-and","repo_url":"https://github.com/nvlabs/gbrl_sb3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"advantage-weighted-regression-simple-and","repo_url":"https://github.com/peisuke/awr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"advantage-weighted-regression-simple-and","repo_url":"https://github.com/xbpeng/awr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"continuous-control","task_name":"Continuous Control"},{"task_slug":"openai-gym","task_name":"OpenAI Gym"},{"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":"regression-1","task_name":"regression"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/openai-gym-on-ant-v2","task":"OpenAI Gym","dataset":"Ant-v2","model":"AWR","rank_in_archive_order":2,"of":2,"metrics":{"Mean Reward":"5067"},"uses_additional_data":false},{"leaderboard":"/sota/openai-gym-on-halfcheetah-v2","task":"OpenAI Gym","dataset":"HalfCheetah-v2","model":"AWR","rank_in_archive_order":2,"of":2,"metrics":{"Mean Reward":"9136"},"uses_additional_data":false},{"leaderboard":"/sota/openai-gym-on-hopper-v2","task":"OpenAI Gym","dataset":"Hopper-v2","model":"AWR","rank_in_archive_order":2,"of":2,"metrics":{"Mean Reward":"3405"},"uses_additional_data":false},{"leaderboard":"/sota/openai-gym-on-humanoid-v2","task":"OpenAI Gym","dataset":"Humanoid-v2","model":"AWR","rank_in_archive_order":1,"of":1,"metrics":{"Average Return":"4996"},"uses_additional_data":false},{"leaderboard":"/sota/openai-gym-on-lunarlander-v2","task":"OpenAI Gym","dataset":"LunarLander-v2","model":"AWR","rank_in_archive_order":2,"of":2,"metrics":{"Average Return":"229"},"uses_additional_data":false},{"leaderboard":"/sota/openai-gym-on-walker2d-v2","task":"OpenAI Gym","dataset":"Walker2d-v2","model":"AWR","rank_in_archive_order":1,"of":2,"metrics":{"Mean Reward":"5813"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1910.00177","atlas_url":"https://app.syntology.ai/?focus=1910.00177","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1910.00177"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1910.00177\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1910.00177"},"call":"get_concepts_for_paper(arxiv_id=\"1910.00177\")"}],"by_repo":[{"repo":"NitinVishalKulkarni/OfflineReinforcementLearning","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"fomorians-oss/awr","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"google/trax","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2110.13711"],"harvested_for_calls":[{"arxiv_id":"2110.13711","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2110.13711"},"call":"get_harvested_code_for_paper(arxiv_id=\"2110.13711\")"}]},{"repo":"nvlabs/gbrl_sb3","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"peisuke/awr","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"xbpeng/awr","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"3203aa28bc75e99bdc818f163953b83606a59e335e3813d0d2bcbb41176932f1","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}