{"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/maximum-total-correlation-reinforcement","title":"Maximum Total Correlation Reinforcement Learning","arxiv_id":"2505.16734","date":"2025-05-22","proceeding":null,"authors":["Bang You","Puze Liu","Huaping Liu","Jan Peters","Oleg Arenz"],"abstract":"Simplicity is a powerful inductive bias. In reinforcement learning, regularization is used for simpler policies, data augmentation for simpler representations, and sparse reward functions for simpler objectives, all that, with the underlying motivation to increase generalizability and robustness by focusing on the essentials. Supplementary to these techniques, we investigate how to promote simple behavior throughout the episode. To that end, we introduce a modification of the reinforcement learning problem that additionally maximizes the total correlation within the induced trajectories. We propose a practical algorithm that optimizes all models, including policy and state representation, based on a lower-bound approximation. In simulated robot environments, our method naturally generates policies that induce periodic and compressible trajectories, and that exhibit superior robustness to noise and changes in dynamics compared to baseline methods, while also improving performance in the original tasks.","url_abs":"https://arxiv.org/abs/2505.16734v1","url_pdf":"https://arxiv.org/pdf/2505.16734v1.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":"maximum-total-correlation-reinforcement","repo_url":"https://github.com/bangyou01/mtc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"inductive-bias","task_name":"Inductive Bias"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.16734","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.16734"}},"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/bangyou01/mtc","reach":null}],"summary":{"ran":6,"ran_draft_wrong":2,"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":11,"samples":[{"code_sha256_prefix":"763fe7eb647a4e12","entry":"Critic","repo":"bangyou01/mtc","repo_kind":"official","path":"tcsac.py","file_url":"https://github.com/bangyou01/mtc/blob/HEAD/tcsac.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"763fe7eb647a4e12"}},{"code_sha256_prefix":"a88818565d321bdc","entry":"IdentityEncoder","repo":"bangyou01/mtc","repo_kind":"official","path":"tcsac.py","file_url":"https://github.com/bangyou01/mtc/blob/HEAD/tcsac.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a88818565d321bdc"}},{"code_sha256_prefix":"2cc86985c2d74f8d","entry":"MLP_encoder","repo":"bangyou01/mtc","repo_kind":"official","path":"tcsac.py","file_url":"https://github.com/bangyou01/mtc/blob/HEAD/tcsac.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2cc86985c2d74f8d"}},{"code_sha256_prefix":"0caf73ff3e17950f","entry":"PixelEncoder","repo":"bangyou01/mtc","repo_kind":"official","path":"tcsac.py","file_url":"https://github.com/bangyou01/mtc/blob/HEAD/tcsac.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0caf73ff3e17950f"}},{"code_sha256_prefix":"c18c053f8218dbbb","entry":"RNNModel","repo":"bangyou01/mtc","repo_kind":"official","path":"tcsac.py","file_url":"https://github.com/bangyou01/mtc/blob/HEAD/tcsac.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c18c053f8218dbbb"}},{"code_sha256_prefix":"82315e6aaed1082e","entry":"Transition_model","repo":"bangyou01/mtc","repo_kind":"official","path":"tcsac.py","file_url":"https://github.com/bangyou01/mtc/blob/HEAD/tcsac.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"82315e6aaed1082e"}},{"code_sha256_prefix":"194b6301d0fceef1","entry":"make_encoder","repo":"bangyou01/mtc","repo_kind":"official","path":"tcsac.py","file_url":"https://github.com/bangyou01/mtc/blob/HEAD/tcsac.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"194b6301d0fceef1"}},{"code_sha256_prefix":"ca7b5ce54979ff79","entry":"safe_atanh","repo":"bangyou01/mtc","repo_kind":"official","path":"tcsac.py","file_url":"https://github.com/bangyou01/mtc/blob/HEAD/tcsac.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ca7b5ce54979ff79"}},{"code_sha256_prefix":"8f578d66fd15da10","entry":"Actor","repo":"bangyou01/mtc","repo_kind":"official","path":"tcsac.py","file_url":"https://github.com/bangyou01/mtc/blob/HEAD/tcsac.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8f578d66fd15da10"}},{"code_sha256_prefix":"206f7671dab40739","entry":"TCSACAgent","repo":"bangyou01/mtc","repo_kind":"official","path":"tcsac.py","file_url":"https://github.com/bangyou01/mtc/blob/HEAD/tcsac.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"206f7671dab40739"}},{"code_sha256_prefix":"bc147ae957bbe3f4","entry":"soft_update_params","repo":"bangyou01/mtc","repo_kind":"official","path":"tcsac.py","file_url":"https://github.com/bangyou01/mtc/blob/HEAD/tcsac.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bc147ae957bbe3f4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}