{"id":25878935,"url":"https://github.com/epignatelli/discovering-reinforcement-learning-algorithms","last_synced_at":"2025-03-02T12:40:05.316Z","repository":{"id":55606768,"uuid":"321378732","full_name":"epignatelli/discovering-reinforcement-learning-algorithms","owner":"epignatelli","description":"A Jax/Stax implementation of the general meta learning paper: Oh, J., Hessel, M., Czarnecki, W.M., Xu, Z., van Hasselt, H.P., Singh, S. and Silver, D., 2020. Discovering reinforcement learning algorithms. Advances in Neural Information Processing Systems, 33.","archived":false,"fork":false,"pushed_at":"2020-12-22T18:32:22.000Z","size":82,"stargazers_count":11,"open_issues_count":1,"forks_count":3,"subscribers_count":1,"default_branch":"main","last_synced_at":"2023-03-10T12:12:13.268Z","etag":null,"topics":["actor-critic","general-meta-learning","jax","lstm","meta-learning","paper-implementations","paper-with-code","policy-gradient","reinforcement-learning","reinforcement-learning-algorithms","rnn","stax"],"latest_commit_sha":null,"homepage":"https://proceedings.neurips.cc/paper/2020/file/0b96d81f0494fde5428c7aea243c9157-Paper.pdf","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/epignatelli.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2020-12-14T14:46:54.000Z","updated_at":"2023-02-06T22:14:26.000Z","dependencies_parsed_at":"2022-08-15T04:10:56.335Z","dependency_job_id":null,"html_url":"https://github.com/epignatelli/discovering-reinforcement-learning-algorithms","commit_stats":null,"previous_names":[],"tags_count":null,"template":null,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/epignatelli%2Fdiscovering-reinforcement-learning-algorithms","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/epignatelli%2Fdiscovering-reinforcement-learning-algorithms/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/epignatelli%2Fdiscovering-reinforcement-learning-algorithms/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/epignatelli%2Fdiscovering-reinforcement-learning-algorithms/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/epignatelli","download_url":"https://codeload.github.com/epignatelli/discovering-reinforcement-learning-algorithms/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":241509592,"owners_count":19974070,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["actor-critic","general-meta-learning","jax","lstm","meta-learning","paper-implementations","paper-with-code","policy-gradient","reinforcement-learning","reinforcement-learning-algorithms","rnn","stax"],"created_at":"2025-03-02T12:40:04.620Z","updated_at":"2025-03-02T12:40:05.284Z","avatar_url":"https://github.com/epignatelli.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"![Build](https://github.com/epignatelli/discovering-reinforcement-learning-algorithms/workflows/build/badge.svg)\n[![Project Status: WIP – Initial development is in progress, but there has not yet been a stable, usable release suitable for the public.](https://www.repostatus.org/badges/latest/wip.svg)](https://www.repostatus.org/#wip)\n[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)\n\n# Discovering reinforcement learning algorithms\nA jax/stax implementation of the NeurIPS 2020 paper: _Discovering reinforcement learning algorithms_ [[1]](https://proceedings.neurips.cc/paper/2020/file/0b96d81f0494fde5428c7aea243c9157-Paper.pdf)\n\nThe agent at `lpg.agent.py` implements the `bsuite.baseline.base.Agent` interface.\nThe `lpg/environments/*.py` interfaces with a `dm_env.Environment`.\nWe wrap the [gym-atari](https://github.com/openai/gym) suite using the `bsuite.utils.gym_wrapper.DMEnvFromGym` adapter into a `dqn.AtariEnv` to implement historical observations and actions repeat.\n\n\n## Installation\nTo run the algorithm on a GPU, I suggest to [install](https://github.com/google/jax#pip-installation) the gpu version of `jax` [[4]](https://github.com/google/jax). You can then install this repo using [Anaconda python](https://www.anaconda.com/products/individual) and [pip](https://pip.pypa.io/en/stable/installing/).\n```sh\nconda env create -n lpg\nconda activate lpg\npip install git+https://github.com/epignatelli/discovering-reinforcement-learning-algorithms\n```\n\n\n## References\n[1] [_Oh, J., Hessel, M., Czarnecki, W.M., Xu, Z., van Hasselt, H.P., Singh, S. and Silver, D., 2020. Discovering reinforcement learning algorithms. Advances in Neural Information Processing Systems, 33._](https://proceedings.neurips.cc/paper/2020/file/0b96d81f0494fde5428c7aea243c9157-Paper.pdf)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fepignatelli%2Fdiscovering-reinforcement-learning-algorithms","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fepignatelli%2Fdiscovering-reinforcement-learning-algorithms","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fepignatelli%2Fdiscovering-reinforcement-learning-algorithms/lists"}