{"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/no-press-diplomacy-modeling-multi-agent","title":"No Press Diplomacy: Modeling Multi-Agent Gameplay","arxiv_id":"1909.02128","date":"2019-09-04","proceeding":null,"authors":["Philip Paquette","Yuchen Lu","Steven Bocco","Max O. Smith","Satya Ortiz-Gagne","Jonathan K. Kummerfeld","Satinder Singh","Joelle Pineau","Aaron Courville"],"abstract":"Diplomacy is a seven-player non-stochastic, non-cooperative game, where agents acquire resources through a mix of teamwork and betrayal. Reliance on trust and coordination makes Diplomacy the first non-cooperative multi-agent benchmark for complex sequential social dilemmas in a rich environment. In this work, we focus on training an agent that learns to play the No Press version of Diplomacy where there is no dedicated communication channel between players. We present DipNet, a neural-network-based policy model for No Press Diplomacy. The model was trained on a new dataset of more than 150,000 human games. Our model is trained by supervised learning (SL) from expert trajectories, which is then used to initialize a reinforcement learning (RL) agent trained through self-play. Both the SL and RL agents demonstrate state-of-the-art No Press performance by beating popular rule-based bots.","url_abs":"https://arxiv.org/abs/1909.02128v2","url_pdf":"https://arxiv.org/pdf/1909.02128v2.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":"no-press-diplomacy-modeling-multi-agent","repo_url":"https://github.com/diplomacy/research","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1909.02128","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.02128"}},"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/diplomacy/research","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":8},"by_repo_kind":{"official":{"samples":8,"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":0,"samples":[{"code_sha256_prefix":"662f356bb95f9d91","entry":"apply_temperature","repo":"diplomacy/research","repo_kind":"official","path":"diplomacy_research/utils/model.py","file_url":"https://github.com/diplomacy/research/blob/HEAD/diplomacy_research/utils/model.py","link_basis":"first_harvest_node","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":"662f356bb95f9d91"}},{"code_sha256_prefix":"caef57af485c2533","entry":"get_game_id","repo":"diplomacy/research","repo_kind":"official","path":"diplomacy_research/models/state_space.py","file_url":"https://github.com/diplomacy/research/blob/HEAD/diplomacy_research/models/state_space.py","link_basis":"first_harvest_node","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":"caef57af485c2533"}},{"code_sha256_prefix":"649a6ee9df5d8a59","entry":"get_player_seed","repo":"diplomacy/research","repo_kind":"official","path":"diplomacy_research/models/state_space.py","file_url":"https://github.com/diplomacy/research/blob/HEAD/diplomacy_research/models/state_space.py","link_basis":"first_harvest_node","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":"649a6ee9df5d8a59"}},{"code_sha256_prefix":"0e99815b63d9de4d","entry":"get_sorted_locs","repo":"diplomacy/research","repo_kind":"official","path":"diplomacy_research/models/state_space.py","file_url":"https://github.com/diplomacy/research/blob/HEAD/diplomacy_research/models/state_space.py","link_basis":"first_harvest_node","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":"0e99815b63d9de4d"}},{"code_sha256_prefix":"91f25470846da737","entry":"handle_queues","repo":"diplomacy/research","repo_kind":"official","path":"diplomacy_research/models/datasets/base_builder.py","file_url":"https://github.com/diplomacy/research/blob/HEAD/diplomacy_research/models/datasets/base_builder.py","link_basis":"first_harvest_node","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":"91f25470846da737"}},{"code_sha256_prefix":"4b5ef01f8c8dcd03","entry":"int_prod","repo":"diplomacy/research","repo_kind":"official","path":"diplomacy_research/utils/model.py","file_url":"https://github.com/diplomacy/research/blob/HEAD/diplomacy_research/utils/model.py","link_basis":"first_harvest_node","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":"4b5ef01f8c8dcd03"}},{"code_sha256_prefix":"9c6a1f4823a6651b","entry":"pad_list","repo":"diplomacy/research","repo_kind":"official","path":"diplomacy_research/utils/model.py","file_url":"https://github.com/diplomacy/research/blob/HEAD/diplomacy_research/utils/model.py","link_basis":"first_harvest_node","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":"9c6a1f4823a6651b"}},{"code_sha256_prefix":"a9af16a3d3977467","entry":"weight_by_order_type","repo":"diplomacy/research","repo_kind":"official","path":"diplomacy_research/players/random_player.py","file_url":"https://github.com/diplomacy/research/blob/HEAD/diplomacy_research/players/random_player.py","link_basis":"first_harvest_node","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":"a9af16a3d3977467"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}