{"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/skill-aware-mutual-information-optimisation","title":"Skill-aware Mutual Information Optimisation for Generalisation in Reinforcement Learning","arxiv_id":"2406.04815","date":"2024-06-07","proceeding":null,"authors":["Xuehui Yu","Mhairi Dunion","Xin Li","Stefano V. Albrecht"],"abstract":"Meta-Reinforcement Learning (Meta-RL) agents can struggle to operate across tasks with varying environmental features that require different optimal skills (i.e., different modes of behaviour). Using context encoders based on contrastive learning to enhance the generalisability of Meta-RL agents is now widely studied but faces challenges such as the requirement for a large sample size, also referred to as the $\\log$-$K$ curse. To improve RL generalisation to different tasks, we first introduce Skill-aware Mutual Information (SaMI), an optimisation objective that aids in distinguishing context embeddings according to skills, thereby equipping RL agents with the ability to identify and execute different skills across tasks. We then propose Skill-aware Noise Contrastive Estimation (SaNCE), a $K$-sample estimator used to optimise the SaMI objective. We provide a framework for equipping an RL agent with SaNCE in practice and conduct experimental validation on modified MuJoCo and Panda-gym benchmarks. We empirically find that RL agents that learn by maximising SaMI achieve substantially improved zero-shot generalisation to unseen tasks. Additionally, the context encoder trained with SaNCE demonstrates greater robustness to a reduction in the number of available samples, thus possessing the potential to overcome the $\\log$-$K$ curse.","url_abs":"https://arxiv.org/abs/2406.04815v3","url_pdf":"https://arxiv.org/pdf/2406.04815v3.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":"skill-aware-mutual-information-optimisation","repo_url":"https://github.com/uoe-agents/sami","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"meta-reinforcement-learning","task_name":"Meta Reinforcement Learning"},{"task_slug":"mujoco","task_name":"MuJoCo"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.04815","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04815"}},"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":"deterministic:regex_extraction","url":"https://github.com/uoe-agents/SaMI","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/uoe-agents/sami","reach":{"status":"ok"}}],"summary":{"ran":3,"ran_draft_wrong":2,"ran_violates":2},"by_repo_kind":{"official":{"samples":7,"ran":7,"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":7,"samples":[{"code_sha256_prefix":"a1a7cce9805bb6af","entry":"InfoNCE","repo":"uoe-agents/sami","repo_kind":"official","path":"algorithm/method_step/info_nce_loss.py","file_url":"https://github.com/uoe-agents/sami/blob/HEAD/algorithm/method_step/info_nce_loss.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":"a1a7cce9805bb6af"}},{"code_sha256_prefix":"c10063e288d48256","entry":"info_nce","repo":"uoe-agents/sami","repo_kind":"official","path":"algorithm/method_step/info_nce_loss.py","file_url":"https://github.com/uoe-agents/sami/blob/HEAD/algorithm/method_step/info_nce_loss.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c10063e288d48256"}},{"code_sha256_prefix":"90286ad8300b6637","entry":"info_nce","repo":"uoe-agents/sami","repo_kind":"official","path":"algorithm/method_step/info_nce_loss.py","file_url":"https://github.com/uoe-agents/sami/blob/HEAD/algorithm/method_step/info_nce_loss.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"90286ad8300b6637"}},{"code_sha256_prefix":"03e6d660e5782677","entry":"info_nce","repo":"uoe-agents/SaMI","repo_kind":"official","path":"algorithm/method_step/info_nce_loss.py","file_url":"https://github.com/uoe-agents/SaMI/blob/HEAD/algorithm/method_step/info_nce_loss.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":"03e6d660e5782677"}},{"code_sha256_prefix":"984ea32677f90d4b","entry":"moving_average","repo":"uoe-agents/SaMI","repo_kind":"official","path":"logger.py","file_url":"https://github.com/uoe-agents/SaMI/blob/HEAD/logger.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"984ea32677f90d4b"}},{"code_sha256_prefix":"3778d2aa87cc4d43","entry":"transpose","repo":"uoe-agents/sami","repo_kind":"official","path":"algorithm/method_step/info_nce_loss.py","file_url":"https://github.com/uoe-agents/sami/blob/HEAD/algorithm/method_step/info_nce_loss.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3778d2aa87cc4d43"}},{"code_sha256_prefix":"55f1419d4d8c483c","entry":"transpose","repo":"uoe-agents/SaMI","repo_kind":"official","path":"algorithm/method_step/info_nce_loss.py","file_url":"https://github.com/uoe-agents/SaMI/blob/HEAD/algorithm/method_step/info_nce_loss.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"55f1419d4d8c483c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}