{"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/pantheonrl-a-marl-library-for-dynamic","title":"PantheonRL: A MARL Library for Dynamic Training Interactions","arxiv_id":"2112.07013","date":"2021-12-13","proceeding":null,"authors":["Bidipta Sarkar","Aditi Talati","Andy Shih","Dorsa Sadigh"],"abstract":"We present PantheonRL, a multiagent reinforcement learning software package for dynamic training interactions such as round-robin, adaptive, and ad-hoc training. Our package is designed around flexible agent objects that can be easily configured to support different training interactions, and handles fully general multiagent environments with mixed rewards and n agents. Built on top of StableBaselines3, our package works directly with existing powerful deep RL algorithms. Finally, PantheonRL comes with an intuitive yet functional web user interface for configuring experiments and launching multiple asynchronous jobs. Our package can be found at https://github.com/Stanford-ILIAD/PantheonRL.","url_abs":"https://arxiv.org/abs/2112.07013v1","url_pdf":"https://arxiv.org/pdf/2112.07013v1.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":"pantheonrl-a-marl-library-for-dynamic","repo_url":"https://github.com/Stanford-ILIAD/PantheonRL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2112.07013","atlas_url":"https://app.syntology.ai/?focus=2112.07013","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.07013"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/Stanford-ILIAD/PantheonRL","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":9},"by_repo_kind":{"official":{"samples":9,"ran":9,"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":"5742ccbbeea55d95","entry":"calculate_space","repo":"Stanford-ILIAD/PantheonRL","repo_kind":"official","path":"pantheonrl/common/util.py","file_url":"https://github.com/Stanford-ILIAD/PantheonRL/blob/HEAD/pantheonrl/common/util.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5742ccbbeea55d95"}},{"code_sha256_prefix":"e7e69361998f84c0","entry":"dataclass_quick_asdict","repo":"Stanford-ILIAD/PantheonRL","repo_kind":"official","path":"pantheonrl/common/trajsaver.py","file_url":"https://github.com/Stanford-ILIAD/PantheonRL/blob/HEAD/pantheonrl/common/trajsaver.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e7e69361998f84c0"}},{"code_sha256_prefix":"1005123632875338","entry":"extract_obs","repo":"Stanford-ILIAD/PantheonRL","repo_kind":"official","path":"pantheonrl/common/observation.py","file_url":"https://github.com/Stanford-ILIAD/PantheonRL/blob/HEAD/pantheonrl/common/observation.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1005123632875338"}},{"code_sha256_prefix":"ecf30766f5776b7c","entry":"extract_partial_obs","repo":"Stanford-ILIAD/PantheonRL","repo_kind":"official","path":"pantheonrl/common/observation.py","file_url":"https://github.com/Stanford-ILIAD/PantheonRL/blob/HEAD/pantheonrl/common/observation.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ecf30766f5776b7c"}},{"code_sha256_prefix":"ef33952ecde12340","entry":"get_L2_sphere","repo":"Stanford-ILIAD/PantheonRL","repo_kind":"official","path":"pantheonrl/algos/adap/util.py","file_url":"https://github.com/Stanford-ILIAD/PantheonRL/blob/HEAD/pantheonrl/algos/adap/util.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ef33952ecde12340"}},{"code_sha256_prefix":"df6a9974418bb1ed","entry":"get_default_obs","repo":"Stanford-ILIAD/PantheonRL","repo_kind":"official","path":"pantheonrl/common/util.py","file_url":"https://github.com/Stanford-ILIAD/PantheonRL/blob/HEAD/pantheonrl/common/util.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"df6a9974418bb1ed"}},{"code_sha256_prefix":"fb6ab3a1f1defb2a","entry":"get_space_size","repo":"Stanford-ILIAD/PantheonRL","repo_kind":"official","path":"pantheonrl/common/util.py","file_url":"https://github.com/Stanford-ILIAD/PantheonRL/blob/HEAD/pantheonrl/common/util.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fb6ab3a1f1defb2a"}},{"code_sha256_prefix":"865642e814e5a593","entry":"get_unit_square","repo":"Stanford-ILIAD/PantheonRL","repo_kind":"official","path":"pantheonrl/algos/adap/util.py","file_url":"https://github.com/Stanford-ILIAD/PantheonRL/blob/HEAD/pantheonrl/algos/adap/util.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"865642e814e5a593"}},{"code_sha256_prefix":"a3a303088488f5f0","entry":"transitions_collate_fn","repo":"Stanford-ILIAD/PantheonRL","repo_kind":"official","path":"pantheonrl/common/trajsaver.py","file_url":"https://github.com/Stanford-ILIAD/PantheonRL/blob/HEAD/pantheonrl/common/trajsaver.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a3a303088488f5f0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}