{"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-distributional-analogue-to-the-successor","title":"A Distributional Analogue to the Successor Representation","arxiv_id":"2402.08530","date":"2024-02-13","proceeding":null,"authors":["Harley Wiltzer","Jesse Farebrother","Arthur Gretton","Yunhao Tang","André Barreto","Will Dabney","Marc G. Bellemare","Mark Rowland"],"abstract":"This paper contributes a new approach for distributional reinforcement learning which elucidates a clean separation of transition structure and reward in the learning process. Analogous to how the successor representation (SR) describes the expected consequences of behaving according to a given policy, our distributional successor measure (SM) describes the distributional consequences of this behaviour. We formulate the distributional SM as a distribution over distributions and provide theory connecting it with distributional and model-based reinforcement learning. Moreover, we propose an algorithm that learns the distributional SM from data by minimizing a two-level maximum mean discrepancy. Key to our method are a number of algorithmic techniques that are independently valuable for learning generative models of state. As an illustration of the usefulness of the distributional SM, we show that it enables zero-shot risk-sensitive policy evaluation in a way that was not previously possible.","url_abs":"https://arxiv.org/abs/2402.08530v2","url_pdf":"https://arxiv.org/pdf/2402.08530v2.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-distributional-analogue-to-the-successor","repo_url":"https://github.com/jessefarebro/distributional-sr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null}],"tasks":[{"task_slug":"distributional-reinforcement-learning","task_name":"Distributional Reinforcement Learning"},{"task_slug":"model-based-reinforcement-learning","task_name":"Model-based Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2402.08530","atlas_url":"https://app.syntology.ai/?focus=2402.08530","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.08530"}},"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/jessefarebro/distributional-sr","reach":null}],"summary":{"ran_draft_wrong":2,"unverified":2},"by_repo_kind":{"official":{"samples":4,"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":0,"samples":[{"code_sha256_prefix":"966cb709a6527c2e","entry":"mmd","repo":"jessefarebro/distributional-sr","repo_kind":"official","path":"dsm/kernels.py","file_url":"https://github.com/jessefarebro/distributional-sr/blob/HEAD/dsm/kernels.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"966cb709a6527c2e"}},{"code_sha256_prefix":"df8b6377f268473b","entry":"pairwise_distance","repo":"jessefarebro/distributional-sr","repo_kind":"official","path":"dsm/kernels.py","file_url":"https://github.com/jessefarebro/distributional-sr/blob/HEAD/dsm/kernels.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"df8b6377f268473b"}},{"code_sha256_prefix":"3c34c7e8ff732ebf","entry":"DistanceFunction","repo":"jessefarebro/distributional-sr","repo_kind":"official","path":"dsm/kernels.py","file_url":"https://github.com/jessefarebro/distributional-sr/blob/HEAD/dsm/kernels.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":"3c34c7e8ff732ebf"}},{"code_sha256_prefix":"b8f8e64c881235c8","entry":"Kernel","repo":"jessefarebro/distributional-sr","repo_kind":"official","path":"dsm/kernels.py","file_url":"https://github.com/jessefarebro/distributional-sr/blob/HEAD/dsm/kernels.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":"b8f8e64c881235c8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}