{"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/meta-gradient-reinforcement-learning","title":"Meta-Gradient Reinforcement Learning","arxiv_id":"1805.09801","date":"2018-05-24","proceeding":"NeurIPS 2018 12","authors":["Zhongwen Xu","Hado van Hasselt","David Silver"],"abstract":"The goal of reinforcement learning algorithms is to estimate and/or optimise\nthe value function. However, unlike supervised learning, no teacher or oracle\nis available to provide the true value function. Instead, the majority of\nreinforcement learning algorithms estimate and/or optimise a proxy for the\nvalue function. This proxy is typically based on a sampled and bootstrapped\napproximation to the true value function, known as a return. The particular\nchoice of return is one of the chief components determining the nature of the\nalgorithm: the rate at which future rewards are discounted; when and how values\nshould be bootstrapped; or even the nature of the rewards themselves. It is\nwell-known that these decisions are crucial to the overall success of RL\nalgorithms. We discuss a gradient-based meta-learning algorithm that is able to\nadapt the nature of the return, online, whilst interacting and learning from\nthe environment. When applied to 57 games on the Atari 2600 environment over\n200 million frames, our algorithm achieved a new state-of-the-art performance.","url_abs":"http://arxiv.org/abs/1805.09801v1","url_pdf":"http://arxiv.org/pdf/1805.09801v1.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":"meta-gradient-reinforcement-learning","repo_url":"https://github.com/RobvanGastel/meta-rl-algorithms","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"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":{"atlas_url":"https://app.syntology.ai/?focus=1805.09801","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.09801"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/RobvanGastel/meta-rl-algorithms","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":4},"by_repo_kind":{"listed":{"samples":4,"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":"85f38abd91775356","entry":"discount_cumsum","repo":"RobvanGastel/meta-rl-algorithms","repo_kind":"listed","path":"algos/mg_a2c/buffer.py","file_url":"https://github.com/RobvanGastel/meta-rl-algorithms/blob/HEAD/algos/mg_a2c/buffer.py","link_basis":"harvester_set","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":"85f38abd91775356"}},{"code_sha256_prefix":"29d380560ab46818","entry":"evaluate_policy","repo":"RobvanGastel/meta-rl-algorithms","repo_kind":"listed","path":"algos/rl2_ppo/learning.py","file_url":"https://github.com/RobvanGastel/meta-rl-algorithms/blob/HEAD/algos/rl2_ppo/learning.py","link_basis":"harvester_set","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":"29d380560ab46818"}},{"code_sha256_prefix":"e12d84ba1f73ff01","entry":"layer_init","repo":"RobvanGastel/meta-rl-algorithms","repo_kind":"listed","path":"utils/misc.py","file_url":"https://github.com/RobvanGastel/meta-rl-algorithms/blob/HEAD/utils/misc.py","link_basis":"harvester_set","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":"e12d84ba1f73ff01"}},{"code_sha256_prefix":"6686f013f3e2c3bf","entry":"mlp","repo":"RobvanGastel/meta-rl-algorithms","repo_kind":"listed","path":"utils/misc.py","file_url":"https://github.com/RobvanGastel/meta-rl-algorithms/blob/HEAD/utils/misc.py","link_basis":"harvester_set","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":"6686f013f3e2c3bf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}