{"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/deep-successor-reinforcement-learning","title":"Deep Successor Reinforcement Learning","arxiv_id":"1606.02396","date":"2016-06-08","proceeding":null,"authors":["Tejas D. Kulkarni","Ardavan Saeedi","Simanta Gautam","Samuel J. Gershman"],"abstract":"Learning robust value functions given raw observations and rewards is now\npossible with model-free and model-based deep reinforcement learning\nalgorithms. There is a third alternative, called Successor Representations\n(SR), which decomposes the value function into two components -- a reward\npredictor and a successor map. The successor map represents the expected future\nstate occupancy from any given state and the reward predictor maps states to\nscalar rewards. The value function of a state can be computed as the inner\nproduct between the successor map and the reward weights. In this paper, we\npresent DSR, which generalizes SR within an end-to-end deep reinforcement\nlearning framework. DSR has several appealing properties including: increased\nsensitivity to distal reward changes due to factorization of reward and world\ndynamics, and the ability to extract bottleneck states (subgoals) given\nsuccessor maps trained under a random policy. We show the efficacy of our\napproach on two diverse environments given raw pixel observations -- simple\ngrid-world domains (MazeBase) and the Doom game engine.","url_abs":"http://arxiv.org/abs/1606.02396v1","url_pdf":"http://arxiv.org/pdf/1606.02396v1.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":"deep-successor-reinforcement-learning","repo_url":"https://github.com/Ardavans/DSR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"fps-games","task_name":"FPS Games"},{"task_slug":"game-of-doom","task_name":"Game of Doom"},{"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/1606.02396","atlas_url":"https://app.syntology.ai/?focus=1606.02396","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.02396"}},"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/Ardavans/DSR","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"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":"734ef573d15eb87b","entry":"get_state","repo":"Ardavans/DSR","repo_kind":"official","path":"dsr/doom.py","file_url":"https://github.com/Ardavans/DSR/blob/HEAD/dsr/doom.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":"734ef573d15eb87b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}