{"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/attentive-multi-task-deep-reinforcement","title":"Attentive Multi-Task Deep Reinforcement Learning","arxiv_id":"1907.02874","date":"2019-07-05","proceeding":null,"authors":["Timo Bram","Gino Brunner","Oliver Richter","Roger Wattenhofer"],"abstract":"Sharing knowledge between tasks is vital for efficient learning in a multi-task setting. However, most research so far has focused on the easier case where knowledge transfer is not harmful, i.e., where knowledge from one task cannot negatively impact the performance on another task. In contrast, we present an approach to multi-task deep reinforcement learning based on attention that does not require any a-priori assumptions about the relationships between tasks. Our attention network automatically groups task knowledge into sub-networks on a state level granularity. It thereby achieves positive knowledge transfer if possible, and avoids negative transfer in cases where tasks interfere. We test our algorithm against two state-of-the-art multi-task/transfer learning approaches and show comparable or superior performance while requiring fewer network parameters.","url_abs":"https://arxiv.org/abs/1907.02874v1","url_pdf":"https://arxiv.org/pdf/1907.02874v1.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":"attentive-multi-task-deep-reinforcement","repo_url":"https://github.com/braemt/attentive-multi-task-deep-reinforcement-learning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"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":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1907.02874","atlas_url":"https://app.syntology.ai/?focus=1907.02874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.02874"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/braemt/attentive-multi-task-deep-reinforcement-learning","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"unverified":5},"by_repo_kind":{"official":{"samples":7,"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":5,"samples":[{"code_sha256_prefix":"1e1712b2e9449aaf","entry":"flatten","repo":"braemt/attentive-multi-task-deep-reinforcement-learning","repo_kind":"official","path":"model.py","file_url":"https://github.com/braemt/attentive-multi-task-deep-reinforcement-learning/blob/HEAD/model.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1e1712b2e9449aaf"}},{"code_sha256_prefix":"ef2d50dfca29c664","entry":"normalized_columns_initializer","repo":"braemt/attentive-multi-task-deep-reinforcement-learning","repo_kind":"official","path":"model.py","file_url":"https://github.com/braemt/attentive-multi-task-deep-reinforcement-learning/blob/HEAD/model.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ef2d50dfca29c664"}},{"code_sha256_prefix":"cd93ba6e9cbcdcb0","entry":"ascii_art_to_uint8_nparray","repo":"braemt/attentive-multi-task-deep-reinforcement-learning","repo_kind":"official","path":"environments/gym_pycolab/ascii_art.py","file_url":"https://github.com/braemt/attentive-multi-task-deep-reinforcement-learning/blob/HEAD/environments/gym_pycolab/ascii_art.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":false,"mcp_get_code":{"code_sha256":"cd93ba6e9cbcdcb0"}},{"code_sha256_prefix":"efb159661f0b9fcf","entry":"cluster_spec","repo":"braemt/attentive-multi-task-deep-reinforcement-learning","repo_kind":"official","path":"worker.py","file_url":"https://github.com/braemt/attentive-multi-task-deep-reinforcement-learning/blob/HEAD/worker.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":false,"mcp_get_code":{"code_sha256":"efb159661f0b9fcf"}},{"code_sha256_prefix":"ae49b6565467a676","entry":"conv2d","repo":"braemt/attentive-multi-task-deep-reinforcement-learning","repo_kind":"official","path":"model.py","file_url":"https://github.com/braemt/attentive-multi-task-deep-reinforcement-learning/blob/HEAD/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":false,"mcp_get_code":{"code_sha256":"ae49b6565467a676"}},{"code_sha256_prefix":"0ca7ce32a4f2492c","entry":"discount","repo":"braemt/attentive-multi-task-deep-reinforcement-learning","repo_kind":"official","path":"a3c.py","file_url":"https://github.com/braemt/attentive-multi-task-deep-reinforcement-learning/blob/HEAD/a3c.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":false,"mcp_get_code":{"code_sha256":"0ca7ce32a4f2492c"}},{"code_sha256_prefix":"9fa49cd4c758655d","entry":"process_rollout","repo":"braemt/attentive-multi-task-deep-reinforcement-learning","repo_kind":"official","path":"a3c.py","file_url":"https://github.com/braemt/attentive-multi-task-deep-reinforcement-learning/blob/HEAD/a3c.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":false,"mcp_get_code":{"code_sha256":"9fa49cd4c758655d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}