{"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":"/task/multi-agent-reinforcement-learning/papers/18","list_of":"/task/multi-agent-reinforcement-learning","task":"Multi-agent Reinforcement Learning","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":18,"pages_in_order":18,"rows_per_page":100,"rows":[1701,1718],"of":1718,"counts":{"archive_papers_tagged":1718,"with_a_code_link":522,"where_syntology_ran_a_sample":135,"not_listed_spam_title":0,"listed":1718,"listed_where_code_ran":135,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":119,"every_run_a_failure_of_syntologys_instrument":16,"listed_with_a_run_with_no_instrument_failure":119,"listed_every_run_a_failure_of_syntologys_instrument":16,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/multi-agent-reinforcement-learning","prev":"/task/multi-agent-reinforcement-learning/papers/17","next":null,"papers":[{"url":null,"slug":"intent-aware-multi-agent-reinforcement","title":"Intent-aware Multi-agent Reinforcement Learning","date":"2018-03-06","arxiv_id":"1803.02018","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-bidding-with-multi-agent","title":"Real-Time Bidding with Multi-Agent Reinforcement Learning in Display Advertising","date":"2018-02-27","arxiv_id":"1802.09756","repositories_listed":0,"syntology":null},{"url":null,"slug":"asynchronous-stochastic-approximations-with","title":"Asynchronous stochastic approximations with asymptotically biased errors and deep multi-agent learning","date":"2018-02-22","arxiv_id":"1802.07935","repositories_listed":0,"syntology":null},{"url":null,"slug":"cooperative-multi-agent-reinforcement","title":"Cooperative Multi-Agent Reinforcement Learning for Low-Level Wireless Communication","date":"2018-01-14","arxiv_id":"1801.04541","repositories_listed":0,"syntology":null},{"url":null,"slug":"neuron-as-an-agent","title":"Neuron as an Agent","date":"2018-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"routing-networks-adaptive-selection-of-non","title":"Routing Networks: Adaptive Selection of Non-linear Functions for Multi-Task Learning","date":"2017-11-03","arxiv_id":"1711.01239","repositories_listed":0,"syntology":null},{"url":null,"slug":"parameter-sharing-deep-deterministic-policy","title":"Parameter Sharing Deep Deterministic Policy Gradient for Cooperative Multi-agent Reinforcement Learning","date":"2017-10-01","arxiv_id":"1710.00336","repositories_listed":0,"syntology":null},{"url":null,"slug":"accnet-actor-coordinator-critic-net-for","title":"ACCNet: Actor-Coordinator-Critic Net for \"Learning-to-Communicate\" with Deep Multi-agent Reinforcement Learning","date":"2017-06-10","arxiv_id":"1706.03235","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-safe-interruptibility-for","title":"Dynamic Safe Interruptibility for Decentralized Multi-Agent Reinforcement Learning","date":"2017-04-10","arxiv_id":"1704.02882","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-decentralized-multi-task-multi-agent","title":"Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability","date":"2017-03-17","arxiv_id":"1703.06182","repositories_listed":0,"syntology":null},{"url":null,"slug":"analysing-congestion-problems-in-multi-agent","title":"Analysing Congestion Problems in Multi-agent Reinforcement Learning","date":"2017-02-28","arxiv_id":"1702.08736","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-multi-agent-reinforcement-learning-for","title":"Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving","date":"2016-10-11","arxiv_id":"1610.03295","repositories_listed":0,"syntology":null},{"url":null,"slug":"dialogue-management-based-on-multi-domain","title":"Dialogue Management based on Multi-domain Corpus","date":"2015-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"human-machine-dialogue-as-a-stochastic-game","title":"Human-Machine Dialogue as a Stochastic Game","date":"2015-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-reinforcement-learning-with-1","title":"Multi-agent Reinforcement Learning with Sparse Interactions by Negotiation and Knowledge Transfer","date":"2015-08-21","arxiv_id":"1508.05328","repositories_listed":0,"syntology":null},{"url":null,"slug":"single-agent-vs-multi-agent-techniques-for","title":"Single-Agent vs. Multi-Agent Techniques for Concurrent Reinforcement Learning of Negotiation Dialogue Policies","date":"2014-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-general-framework-for-interacting-bayes","title":"A General Framework for Interacting Bayes-Optimally with Self-Interested Agents using Arbitrary Parametric Model and Model Prior","date":"2013-04-07","arxiv_id":"1304.2024","repositories_listed":0,"syntology":null},{"url":null,"slug":"solving-stochastic-games","title":"Solving Stochastic Games","date":"2009-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"c21772df5ae25f094d3a4d2ba0c86b6c1ab23d14c6ff8898fb87435e9635c3de","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}