{"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/multi-agent-trust-region-policy-optimization","title":"Multi-Agent Trust Region Policy Optimization","arxiv_id":"2010.07916","date":"2020-10-15","proceeding":null,"authors":["Hepeng Li","Haibo He"],"abstract":"We extend trust region policy optimization (TRPO) to multi-agent reinforcement learning (MARL) problems. We show that the policy update of TRPO can be transformed into a distributed consensus optimization problem for multi-agent cases. By making a series of approximations to the consensus optimization model, we propose a decentralized MARL algorithm, which we call multi-agent TRPO (MATRPO). This algorithm can optimize distributed policies based on local observations and private rewards. The agents do not need to know observations, rewards, policies or value/action-value functions of other agents. The agents only share a likelihood ratio with their neighbors during the training process. The algorithm is fully decentralized and privacy-preserving. Our experiments on two cooperative games demonstrate its robust performance on complicated MARL tasks.","url_abs":"https://arxiv.org/abs/2010.07916v3","url_pdf":"https://arxiv.org/pdf/2010.07916v3.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":"multi-agent-trust-region-policy-optimization","repo_url":"https://github.com/hepengli/matrpo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"multi-agent-reinforcement-learning","task_name":"Multi-agent Reinforcement Learning"},{"task_slug":"privacy-preserving","task_name":"Privacy Preserving"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"trpo","method_name":"TRPO"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.07916","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.07916"}},"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/hepengli/matrpo","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"unverified":16},"by_repo_kind":{"listed":{"samples":18,"ran":2,"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":0,"samples":[{"code_sha256_prefix":"0cb9b8299fe38738","entry":"ortho_init","repo":"hepengli/matrpo","repo_kind":"listed","path":"matrpo/common/models.py","file_url":"https://github.com/hepengli/matrpo/blob/HEAD/matrpo/common/models.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0cb9b8299fe38738"}},{"code_sha256_prefix":"a44574392d168384","entry":"register","repo":"hepengli/matrpo","repo_kind":"listed","path":"matrpo/common/models.py","file_url":"https://github.com/hepengli/matrpo/blob/HEAD/matrpo/common/models.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a44574392d168384"}},{"code_sha256_prefix":"e848337651ed8c10","entry":"backtrack","repo":"hepengli/matrpo","repo_kind":"listed","path":"matrpo/common/lbfgs.py","file_url":"https://github.com/hepengli/matrpo/blob/HEAD/matrpo/common/lbfgs.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e848337651ed8c10"}},{"code_sha256_prefix":"e0fa22de3d36e9f1","entry":"cg","repo":"hepengli/matrpo","repo_kind":"listed","path":"matrpo/common/cg.py","file_url":"https://github.com/hepengli/matrpo/blob/HEAD/matrpo/common/cg.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e0fa22de3d36e9f1"}},{"code_sha256_prefix":"2d39cd1166fa0004","entry":"colorize","repo":"hepengli/matrpo","repo_kind":"listed","path":"matrpo/common/console_util.py","file_url":"https://github.com/hepengli/matrpo/blob/HEAD/matrpo/common/console_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2d39cd1166fa0004"}},{"code_sha256_prefix":"b1affaa548a40f17","entry":"conv","repo":"hepengli/matrpo","repo_kind":"listed","path":"matrpo/common/models.py","file_url":"https://github.com/hepengli/matrpo/blob/HEAD/matrpo/common/models.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b1affaa548a40f17"}},{"code_sha256_prefix":"973bd4eccef85757","entry":"discount","repo":"hepengli/matrpo","repo_kind":"listed","path":"matrpo/common/math_util.py","file_url":"https://github.com/hepengli/matrpo/blob/HEAD/matrpo/common/math_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"973bd4eccef85757"}},{"code_sha256_prefix":"4ddc13c7b29053c5","entry":"explained_variance","repo":"hepengli/matrpo","repo_kind":"listed","path":"matrpo/common/math_util.py","file_url":"https://github.com/hepengli/matrpo/blob/HEAD/matrpo/common/math_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4ddc13c7b29053c5"}},{"code_sha256_prefix":"e53a6a3f02175d35","entry":"explained_variance_2d","repo":"hepengli/matrpo","repo_kind":"listed","path":"matrpo/common/math_util.py","file_url":"https://github.com/hepengli/matrpo/blob/HEAD/matrpo/common/math_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e53a6a3f02175d35"}},{"code_sha256_prefix":"157f016aac49c483","entry":"fmt_item","repo":"hepengli/matrpo","repo_kind":"listed","path":"matrpo/common/console_util.py","file_url":"https://github.com/hepengli/matrpo/blob/HEAD/matrpo/common/console_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"157f016aac49c483"}},{"code_sha256_prefix":"d3ac76f7eab8f898","entry":"fmt_row","repo":"hepengli/matrpo","repo_kind":"listed","path":"matrpo/common/console_util.py","file_url":"https://github.com/hepengli/matrpo/blob/HEAD/matrpo/common/console_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d3ac76f7eab8f898"}},{"code_sha256_prefix":"b7d6a34e1010c8d3","entry":"get_wrapper_by_name","repo":"hepengli/matrpo","repo_kind":"listed","path":"matrpo/common/misc_util.py","file_url":"https://github.com/hepengli/matrpo/blob/HEAD/matrpo/common/misc_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b7d6a34e1010c8d3"}},{"code_sha256_prefix":"2bf246102dee2c97","entry":"lbfgs","repo":"hepengli/matrpo","repo_kind":"listed","path":"matrpo/common/lbfgs.py","file_url":"https://github.com/hepengli/matrpo/blob/HEAD/matrpo/common/lbfgs.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2bf246102dee2c97"}},{"code_sha256_prefix":"817d5caf0e3d3706","entry":"make_output_format","repo":"hepengli/matrpo","repo_kind":"listed","path":"matrpo/common/logger.py","file_url":"https://github.com/hepengli/matrpo/blob/HEAD/matrpo/common/logger.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"817d5caf0e3d3706"}},{"code_sha256_prefix":"131bfcd55d2d25cc","entry":"pickle_load","repo":"hepengli/matrpo","repo_kind":"listed","path":"matrpo/common/misc_util.py","file_url":"https://github.com/hepengli/matrpo/blob/HEAD/matrpo/common/misc_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"131bfcd55d2d25cc"}},{"code_sha256_prefix":"accf0e50708b4878","entry":"pretty_eta","repo":"hepengli/matrpo","repo_kind":"listed","path":"matrpo/common/misc_util.py","file_url":"https://github.com/hepengli/matrpo/blob/HEAD/matrpo/common/misc_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"accf0e50708b4878"}},{"code_sha256_prefix":"7bf2cc4ded16fad8","entry":"profile","repo":"hepengli/matrpo","repo_kind":"listed","path":"matrpo/common/logger.py","file_url":"https://github.com/hepengli/matrpo/blob/HEAD/matrpo/common/logger.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7bf2cc4ded16fad8"}},{"code_sha256_prefix":"88ef5a17fc986d9a","entry":"read_json","repo":"hepengli/matrpo","repo_kind":"listed","path":"matrpo/common/logger.py","file_url":"https://github.com/hepengli/matrpo/blob/HEAD/matrpo/common/logger.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"88ef5a17fc986d9a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}