{"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/guided-deep-reinforcement-learning-for-swarm","title":"Guided Deep Reinforcement Learning for Swarm Systems","arxiv_id":"1709.06011","date":"2017-09-18","proceeding":null,"authors":["Maximilian Hüttenrauch","Adrian Šošić","Gerhard Neumann"],"abstract":"In this paper, we investigate how to learn to control a group of cooperative\nagents with limited sensing capabilities such as robot swarms. The agents have\nonly very basic sensor capabilities, yet in a group they can accomplish\nsophisticated tasks, such as distributed assembly or search and rescue tasks.\nLearning a policy for a group of agents is difficult due to distributed partial\nobservability of the state. Here, we follow a guided approach where a critic\nhas central access to the global state during learning, which simplifies the\npolicy evaluation problem from a reinforcement learning point of view. For\nexample, we can get the positions of all robots of the swarm using a camera\nimage of a scene. This camera image is only available to the critic and not to\nthe control policies of the robots. We follow an actor-critic approach, where\nthe actors base their decisions only on locally sensed information. In\ncontrast, the critic is learned based on the true global state. Our algorithm\nuses deep reinforcement learning to approximate both the Q-function and the\npolicy. The performance of the algorithm is evaluated on two tasks with simple\nsimulated 2D agents: 1) finding and maintaining a certain distance to each\nothers and 2) locating a target.","url_abs":"http://arxiv.org/abs/1709.06011v1","url_pdf":"http://arxiv.org/pdf/1709.06011v1.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":"guided-deep-reinforcement-learning-for-swarm","repo_url":"https://github.com/hex-plex/KiloBot-MultiAgent-RL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"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":{"atlas_url":"https://app.syntology.ai/?focus=1709.06011","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1709.06011"}},"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/hex-plex/KiloBot-MultiAgent-RL","reach":null}],"summary":{"ran_draft_wrong":3,"unverified":1},"by_repo_kind":{"listed":{"samples":4,"ran":3,"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":"916aa6d1edd1bc98","entry":"fetch_states_graph","repo":"hex-plex/KiloBot-MultiAgent-RL","repo_kind":"listed","path":"model-train.py","file_url":"https://github.com/hex-plex/KiloBot-MultiAgent-RL/blob/HEAD/model-train.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"916aa6d1edd1bc98"}},{"code_sha256_prefix":"573bad30e2eb8797","entry":"fetch_states_localize","repo":"hex-plex/KiloBot-MultiAgent-RL","repo_kind":"listed","path":"model-train.py","file_url":"https://github.com/hex-plex/KiloBot-MultiAgent-RL/blob/HEAD/model-train.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"573bad30e2eb8797"}},{"code_sha256_prefix":"5bc08ac0fdda1114","entry":"fetch_states_localize","repo":"hex-plex/KiloBot-MultiAgent-RL","repo_kind":"listed","path":"play-model.py","file_url":"https://github.com/hex-plex/KiloBot-MultiAgent-RL/blob/HEAD/play-model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5bc08ac0fdda1114"}},{"code_sha256_prefix":"6912dfe99280e57a","entry":"preprocessReplayBuffer","repo":"hex-plex/KiloBot-MultiAgent-RL","repo_kind":"listed","path":"model-train.py","file_url":"https://github.com/hex-plex/KiloBot-MultiAgent-RL/blob/HEAD/model-train.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":"6912dfe99280e57a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}