{"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/the-potential-of-the-return-distribution-for","title":"The Potential of the Return Distribution for Exploration in RL","arxiv_id":"1806.04242","date":"2018-06-11","proceeding":null,"authors":["Thomas M. Moerland","Joost Broekens","Catholijn M. Jonker"],"abstract":"This paper studies the potential of the return distribution for exploration\nin deterministic reinforcement learning (RL) environments. We study network\nlosses and propagation mechanisms for Gaussian, Categorical and Gaussian\nmixture distributions. Combined with exploration policies that leverage this\nreturn distribution, we solve, for example, a randomized Chain task of length\n100, which has not been reported before when learning with neural networks.","url_abs":"http://arxiv.org/abs/1806.04242v2","url_pdf":"http://arxiv.org/pdf/1806.04242v2.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":"the-potential-of-the-return-distribution-for","repo_url":"https://github.com/tmoer/return_distribution_exploration","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"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/1806.04242","atlas_url":"https://app.syntology.ai/?focus=1806.04242","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.04242"}},"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/tmoer/return_distribution_exploration","reach":null}],"summary":{"ran_violates":1,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"3143a4dca90a4666","entry":"correct_dim","repo":"tmoer/return_distribution_exploration","repo_kind":"official","path":"duvn_agent.py","file_url":"https://github.com/tmoer/return_distribution_exploration/blob/HEAD/duvn_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3143a4dca90a4666"}},{"code_sha256_prefix":"cafbf7fcceb3dba1","entry":"get_number_output_parameters","repo":"tmoer/return_distribution_exploration","repo_kind":"official","path":"network/distributions.py","file_url":"https://github.com/tmoer/return_distribution_exploration/blob/HEAD/network/distributions.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cafbf7fcceb3dba1"}},{"code_sha256_prefix":"14d43170bb5666d4","entry":"train","repo":"tmoer/return_distribution_exploration","repo_kind":"official","path":"duvn_agent.py","file_url":"https://github.com/tmoer/return_distribution_exploration/blob/HEAD/duvn_agent.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":"14d43170bb5666d4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}