{"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/a-consciousness-inspired-planning-agent-for","title":"A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning","arxiv_id":"2106.02097","date":"2021-06-03","proceeding":"NeurIPS 2021 12","authors":["Mingde Zhao","Zhen Liu","Sitao Luan","Shuyuan Zhang","Doina Precup","Yoshua Bengio"],"abstract":"We present an end-to-end, model-based deep reinforcement learning agent which dynamically attends to relevant parts of its state during planning. The agent uses a bottleneck mechanism over a set-based representation to force the number of entities to which the agent attends at each planning step to be small. In experiments, we investigate the bottleneck mechanism with several sets of customized environments featuring different challenges. We consistently observe that the design allows the planning agents to generalize their learned task-solving abilities in compatible unseen environments by attending to the relevant objects, leading to better out-of-distribution generalization performance.","url_abs":"https://arxiv.org/abs/2106.02097v3","url_pdf":"https://arxiv.org/pdf/2106.02097v3.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":"a-consciousness-inspired-planning-agent-for","repo_url":"https://github.com/mila-iqia/conscious-planning","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"model-based-reinforcement-learning","task_name":"Model-based Reinforcement Learning"},{"task_slug":"out-of-distribution-generalization","task_name":"Out-of-Distribution Generalization"},{"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":{"syntology_url":"https://syntology.ai/paper/2106.02097","atlas_url":"https://app.syntology.ai/?focus=2106.02097","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.02097"}},"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":"deterministic:regex_extraction","url":"https://github.com/PwnerHarry/CP","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mila-iqia/conscious-planning","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"ran_fixture":1,"unverified":3},"by_repo_kind":{"found_in_text":{"samples":7,"ran":4,"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":"16c1cdf7d8a36c9a","entry":"MultiHeadAttention","repo":"PwnerHarry/CP","repo_kind":"found_in_text","path":"components_CP.py","file_url":"https://github.com/PwnerHarry/CP/blob/HEAD/components_CP.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"16c1cdf7d8a36c9a"}},{"code_sha256_prefix":"2ba23d13544a5585","entry":"SUBLAYER_TRANSFORMER_ACTION","repo":"PwnerHarry/CP","repo_kind":"found_in_text","path":"components_CP.py","file_url":"https://github.com/PwnerHarry/CP/blob/HEAD/components_CP.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2ba23d13544a5585"}},{"code_sha256_prefix":"8ef8755750a2c4f2","entry":"SUBLAYER_TRANSFORMER_FC","repo":"PwnerHarry/CP","repo_kind":"found_in_text","path":"components_CP.py","file_url":"https://github.com/PwnerHarry/CP/blob/HEAD/components_CP.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8ef8755750a2c4f2"}},{"code_sha256_prefix":"cd1c640990b1df7e","entry":"scaled_dot_product_attention","repo":"PwnerHarry/CP","repo_kind":"found_in_text","path":"components_CP.py","file_url":"https://github.com/PwnerHarry/CP/blob/HEAD/components_CP.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cd1c640990b1df7e"}},{"code_sha256_prefix":"188def752b40547d","entry":"COMPRESSOR_SET","repo":"PwnerHarry/CP","repo_kind":"found_in_text","path":"components_CP.py","file_url":"https://github.com/PwnerHarry/CP/blob/HEAD/components_CP.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":"188def752b40547d"}},{"code_sha256_prefix":"930c477c45a18563","entry":"SUBLAYER_TRANSFORMER_MHA","repo":"PwnerHarry/CP","repo_kind":"found_in_text","path":"components_CP.py","file_url":"https://github.com/PwnerHarry/CP/blob/HEAD/components_CP.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":"930c477c45a18563"}},{"code_sha256_prefix":"e3dd893cf9205b0e","entry":"TRANSFORMER_AUGMENTED","repo":"PwnerHarry/CP","repo_kind":"found_in_text","path":"components_CP.py","file_url":"https://github.com/PwnerHarry/CP/blob/HEAD/components_CP.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":"e3dd893cf9205b0e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}