{"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-reinforcement-learning-for-2","title":"Multi-agent Reinforcement Learning for Networked System Control","arxiv_id":"2004.01339","date":"2020-04-03","proceeding":"ICLR 2020 1","authors":["Tianshu Chu","Sandeep Chinchali","Sachin Katti"],"abstract":"This paper considers multi-agent reinforcement learning (MARL) in networked system control. Specifically, each agent learns a decentralized control policy based on local observations and messages from connected neighbors. We formulate such a networked MARL (NMARL) problem as a spatiotemporal Markov decision process and introduce a spatial discount factor to stabilize the training of each local agent. Further, we propose a new differentiable communication protocol, called NeurComm, to reduce information loss and non-stationarity in NMARL. Based on experiments in realistic NMARL scenarios of adaptive traffic signal control and cooperative adaptive cruise control, an appropriate spatial discount factor effectively enhances the learning curves of non-communicative MARL algorithms, while NeurComm outperforms existing communication protocols in both learning efficiency and control performance.","url_abs":"https://arxiv.org/abs/2004.01339v2","url_pdf":"https://arxiv.org/pdf/2004.01339v2.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-reinforcement-learning-for-2","repo_url":"https://github.com/cts198859/deeprl_network","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"multi-agent-reinforcement-learning","task_name":"Multi-agent Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"traffic-signal-control","task_name":"Traffic Signal Control"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2004.01339","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.01339"}},"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/cts198859/deeprl_network","reach":null}],"summary":{"ran_draft_wrong":1,"ran_honours":1,"unverified":14},"by_repo_kind":{"official":{"samples":16,"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":16,"samples":[{"code_sha256_prefix":"6583a667fee3e221","entry":"ortho_init","repo":"cts198859/deeprl_network","repo_kind":"official","path":"agents/models.py","file_url":"https://github.com/cts198859/deeprl_network/blob/HEAD/agents/models.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6583a667fee3e221"}},{"code_sha256_prefix":"8073391fdb18d328","entry":"seq_to_batch","repo":"cts198859/deeprl_network","repo_kind":"official","path":"agents/models.py","file_url":"https://github.com/cts198859/deeprl_network/blob/HEAD/agents/models.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8073391fdb18d328"}},{"code_sha256_prefix":"f33f9b4bd9416ae2","entry":"IA2C","repo":"cts198859/deeprl_network","repo_kind":"official","path":"agents/models.py","file_url":"https://github.com/cts198859/deeprl_network/blob/HEAD/agents/models.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":"f33f9b4bd9416ae2"}},{"code_sha256_prefix":"5a202858eb418a3c","entry":"LstmPolicy","repo":"cts198859/deeprl_network","repo_kind":"official","path":"agents/models.py","file_url":"https://github.com/cts198859/deeprl_network/blob/HEAD/agents/models.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":"5a202858eb418a3c"}},{"code_sha256_prefix":"449b91229d1ece26","entry":"MA2C_NC","repo":"cts198859/deeprl_network","repo_kind":"official","path":"agents/models.py","file_url":"https://github.com/cts198859/deeprl_network/blob/HEAD/agents/models.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":"449b91229d1ece26"}},{"code_sha256_prefix":"33437057a34d050f","entry":"MultiAgentOnPolicyBuffer","repo":"cts198859/deeprl_network","repo_kind":"official","path":"agents/models.py","file_url":"https://github.com/cts198859/deeprl_network/blob/HEAD/agents/models.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":"33437057a34d050f"}},{"code_sha256_prefix":"640ec1d272f2f995","entry":"NCMultiAgentPolicy","repo":"cts198859/deeprl_network","repo_kind":"official","path":"agents/models.py","file_url":"https://github.com/cts198859/deeprl_network/blob/HEAD/agents/models.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":"640ec1d272f2f995"}},{"code_sha256_prefix":"dfa6c7cdc42108c9","entry":"OnPolicyBuffer","repo":"cts198859/deeprl_network","repo_kind":"official","path":"agents/models.py","file_url":"https://github.com/cts198859/deeprl_network/blob/HEAD/agents/models.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":"dfa6c7cdc42108c9"}},{"code_sha256_prefix":"e9f4e2bdaca97b40","entry":"Policy","repo":"cts198859/deeprl_network","repo_kind":"official","path":"agents/models.py","file_url":"https://github.com/cts198859/deeprl_network/blob/HEAD/agents/models.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":"e9f4e2bdaca97b40"}},{"code_sha256_prefix":"c6875fcebddc4cb5","entry":"Scheduler","repo":"cts198859/deeprl_network","repo_kind":"official","path":"agents/models.py","file_url":"https://github.com/cts198859/deeprl_network/blob/HEAD/agents/models.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":"c6875fcebddc4cb5"}},{"code_sha256_prefix":"ec90622279020749","entry":"TransBuffer","repo":"cts198859/deeprl_network","repo_kind":"official","path":"agents/models.py","file_url":"https://github.com/cts198859/deeprl_network/blob/HEAD/agents/models.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":"ec90622279020749"}},{"code_sha256_prefix":"7b819ded1e1db41d","entry":"batch_to_seq","repo":"cts198859/deeprl_network","repo_kind":"official","path":"agents/models.py","file_url":"https://github.com/cts198859/deeprl_network/blob/HEAD/agents/models.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":"7b819ded1e1db41d"}},{"code_sha256_prefix":"2e3728ff64410ef8","entry":"fc","repo":"cts198859/deeprl_network","repo_kind":"official","path":"agents/models.py","file_url":"https://github.com/cts198859/deeprl_network/blob/HEAD/agents/models.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":"2e3728ff64410ef8"}},{"code_sha256_prefix":"7adc90aced43e4d6","entry":"lstm","repo":"cts198859/deeprl_network","repo_kind":"official","path":"agents/models.py","file_url":"https://github.com/cts198859/deeprl_network/blob/HEAD/agents/models.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":"7adc90aced43e4d6"}},{"code_sha256_prefix":"a13c90852236eb4c","entry":"lstm_comm","repo":"cts198859/deeprl_network","repo_kind":"official","path":"agents/models.py","file_url":"https://github.com/cts198859/deeprl_network/blob/HEAD/agents/models.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":"a13c90852236eb4c"}},{"code_sha256_prefix":"64fc6fd36927d635","entry":"lstm_comm_hetero","repo":"cts198859/deeprl_network","repo_kind":"official","path":"agents/models.py","file_url":"https://github.com/cts198859/deeprl_network/blob/HEAD/agents/models.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":"64fc6fd36927d635"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}