{"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/information-asymmetry-in-kl-regularized-rl-1","title":"Information asymmetry in KL-regularized RL","arxiv_id":"1905.01240","date":"2019-05-03","proceeding":"ICLR 2019 5","authors":["Alexandre Galashov","Siddhant M. Jayakumar","Leonard Hasenclever","Dhruva Tirumala","Jonathan Schwarz","Guillaume Desjardins","Wojciech M. Czarnecki","Yee Whye Teh","Razvan Pascanu","Nicolas Heess"],"abstract":"Many real world tasks exhibit rich structure that is repeated across different parts of the state space or in time. In this work we study the possibility of leveraging such repeated structure to speed up and regularize learning. We start from the KL regularized expected reward objective which introduces an additional component, a default policy. Instead of relying on a fixed default policy, we learn it from data. But crucially, we restrict the amount of information the default policy receives, forcing it to learn reusable behaviors that help the policy learn faster. We formalize this strategy and discuss connections to information bottleneck approaches and to the variational EM algorithm. We present empirical results in both discrete and continuous action domains and demonstrate that, for certain tasks, learning a default policy alongside the policy can significantly speed up and improve learning.","url_abs":"https://arxiv.org/abs/1905.01240v1","url_pdf":"https://arxiv.org/pdf/1905.01240v1.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":"information-asymmetry-in-kl-regularized-rl-1","repo_url":"https://github.com/RobvanGastel/svg-priors","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1905.01240","atlas_url":"https://app.syntology.ai/?focus=1905.01240","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.01240"}},"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/RobvanGastel/svg-priors","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"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":"7569e2a512ec417c","entry":"mlp","repo":"RobvanGastel/svg-priors","repo_kind":"listed","path":"utils/misc.py","file_url":"https://github.com/RobvanGastel/svg-priors/blob/HEAD/utils/misc.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7569e2a512ec417c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}