{"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/multi-view-disentanglement-for-reinforcement","title":"Multi-view Disentanglement for Reinforcement Learning with Multiple Cameras","arxiv_id":"2404.14064","date":"2024-04-22","proceeding":null,"authors":["Mhairi Dunion","Stefano V. Albrecht"],"abstract":"The performance of image-based Reinforcement Learning (RL) agents can vary depending on the position of the camera used to capture the images. Training on multiple cameras simultaneously, including a first-person egocentric camera, can leverage information from different camera perspectives to improve the performance of RL. However, hardware constraints may limit the availability of multiple cameras in real-world deployment. Additionally, cameras may become damaged in the real-world preventing access to all cameras that were used during training. To overcome these hardware constraints, we propose Multi-View Disentanglement (MVD), which uses multiple cameras to learn a policy that is robust to a reduction in the number of cameras to generalise to any single camera from the training set. Our approach is a self-supervised auxiliary task for RL that learns a disentangled representation from multiple cameras, with a shared representation that is aligned across all cameras to allow generalisation to a single camera, and a private representation that is camera-specific. We show experimentally that an RL agent trained on a single third-person camera is unable to learn an optimal policy in many control tasks; but, our approach, benefiting from multiple cameras during training, is able to solve the task using only the same single third-person camera.","url_abs":"https://arxiv.org/abs/2404.14064v2","url_pdf":"https://arxiv.org/pdf/2404.14064v2.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":"multi-view-disentanglement-for-reinforcement","repo_url":"https://github.com/uoe-agents/mvd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"disentanglement","task_name":"Disentanglement"},{"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/2404.14064","atlas_url":"https://app.syntology.ai/?focus=2404.14064","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.14064"}},"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/uoe-agents/mvd","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"ran_draft_wrong":1,"ran_fixture":1,"ran_honours":1,"ran_violates":1,"unverified":3},"by_repo_kind":{"official":{"samples":11,"ran":8,"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":"b5e5ec5ae2bf2ea6","entry":"cosine_distance","repo":"uoe-agents/mvd","repo_kind":"official","path":"algorithms/info_nce.py","file_url":"https://github.com/uoe-agents/mvd/blob/HEAD/algorithms/info_nce.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b5e5ec5ae2bf2ea6"}},{"code_sha256_prefix":"c105e24c6a7befa4","entry":"info_nce","repo":"uoe-agents/mvd","repo_kind":"official","path":"algorithms/info_nce.py","file_url":"https://github.com/uoe-agents/mvd/blob/HEAD/algorithms/info_nce.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c105e24c6a7befa4"}},{"code_sha256_prefix":"bdef24507a4ccfa7","entry":"mlp","repo":"uoe-agents/mvd","repo_kind":"official","path":"utils.py","file_url":"https://github.com/uoe-agents/mvd/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bdef24507a4ccfa7"}},{"code_sha256_prefix":"975f23eeea267e55","entry":"preprocess_obs","repo":"uoe-agents/mvd","repo_kind":"official","path":"utils.py","file_url":"https://github.com/uoe-agents/mvd/blob/HEAD/utils.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"975f23eeea267e55"}},{"code_sha256_prefix":"083eee6f7eed5a7d","entry":"rect_prism_tolerance","repo":"uoe-agents/mvd","repo_kind":"official","path":"metaworld/envs/reward_utils.py","file_url":"https://github.com/uoe-agents/mvd/blob/HEAD/metaworld/envs/reward_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"083eee6f7eed5a7d"}},{"code_sha256_prefix":"6ee8c9901ab984a9","entry":"to_np","repo":"uoe-agents/mvd","repo_kind":"official","path":"utils.py","file_url":"https://github.com/uoe-agents/mvd/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6ee8c9901ab984a9"}},{"code_sha256_prefix":"1ab84d50eed1d70e","entry":"tolerance","repo":"uoe-agents/mvd","repo_kind":"official","path":"metaworld/envs/reward_utils.py","file_url":"https://github.com/uoe-agents/mvd/blob/HEAD/metaworld/envs/reward_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1ab84d50eed1d70e"}},{"code_sha256_prefix":"55f1419d4d8c483c","entry":"transpose","repo":"uoe-agents/mvd","repo_kind":"official","path":"algorithms/info_nce.py","file_url":"https://github.com/uoe-agents/mvd/blob/HEAD/algorithms/info_nce.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"55f1419d4d8c483c"}},{"code_sha256_prefix":"e13df24e0d039aa9","entry":"full_v1_path_for","repo":"uoe-agents/mvd","repo_kind":"official","path":"metaworld/envs/asset_path_utils.py","file_url":"https://github.com/uoe-agents/mvd/blob/HEAD/metaworld/envs/asset_path_utils.py","link_basis":"harvester_set","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":"e13df24e0d039aa9"}},{"code_sha256_prefix":"061fee9f0adfe735","entry":"full_v2_path_for","repo":"uoe-agents/mvd","repo_kind":"official","path":"metaworld/envs/asset_path_utils.py","file_url":"https://github.com/uoe-agents/mvd/blob/HEAD/metaworld/envs/asset_path_utils.py","link_basis":"harvester_set","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":"061fee9f0adfe735"}},{"code_sha256_prefix":"e1dac90f131811f7","entry":"inverse_tolerance","repo":"uoe-agents/mvd","repo_kind":"official","path":"metaworld/envs/reward_utils.py","file_url":"https://github.com/uoe-agents/mvd/blob/HEAD/metaworld/envs/reward_utils.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":"e1dac90f131811f7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}