{"id":13689252,"url":"https://github.com/Kaixhin/spinning-up-basic","last_synced_at":"2025-05-01T23:33:15.485Z","repository":{"id":41467407,"uuid":"166422683","full_name":"Kaixhin/spinning-up-basic","owner":"Kaixhin","description":"Basic versions of agents from Spinning Up in Deep RL written in PyTorch","archived":false,"fork":false,"pushed_at":"2021-05-20T06:53:54.000Z","size":804,"stargazers_count":195,"open_issues_count":0,"forks_count":19,"subscribers_count":9,"default_branch":"master","last_synced_at":"2024-08-03T15:16:45.340Z","etag":null,"topics":["deep-learning","deep-reinforcement-learning"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Kaixhin.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE.md","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2019-01-18T15:07:49.000Z","updated_at":"2024-07-17T08:01:38.000Z","dependencies_parsed_at":"2022-09-05T22:13:41.395Z","dependency_job_id":null,"html_url":"https://github.com/Kaixhin/spinning-up-basic","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Kaixhin%2Fspinning-up-basic","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Kaixhin%2Fspinning-up-basic/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Kaixhin%2Fspinning-up-basic/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Kaixhin%2Fspinning-up-basic/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Kaixhin","download_url":"https://codeload.github.com/Kaixhin/spinning-up-basic/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":224282194,"owners_count":17285786,"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":["deep-learning","deep-reinforcement-learning"],"created_at":"2024-08-02T15:01:40.142Z","updated_at":"2024-11-12T13:31:11.131Z","avatar_url":"https://github.com/Kaixhin.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# spinning-up-basic\n\nBasic versions of agents from [Spinning Up in Deep RL](https://spinningup.openai.com/) written in [PyTorch](https://pytorch.org/). Designed to run quickly on CPU on [`Pendulum-v0`](https://gym.openai.com/envs/Pendulum-v0/) from [OpenAI Gym](https://gym.openai.com/).\n\nTo see differences between algorithms, try running `diff -y \u003cfile1\u003e \u003cfile2\u003e`, e.g., `diff -y ddpg.py td3.py`.\n\nFor MPI versions of on-policy algorithms, see the [`mpi` branch](https://github.com/Kaixhin/spinning-up-basic/tree/mpi).\n\n## Algorithms\n\n- [Vanilla Policy Gradient](https://spinningup.openai.com/en/latest/algorithms/vpg.html)/Advantage Actor-Critic (`vpg.py`)\n- [Trust Region Policy Gradient](https://spinningup.openai.com/en/latest/algorithms/trpo.html) (`trpo.py`)\n- [Proximal Policy Optimization](https://spinningup.openai.com/en/latest/algorithms/ppo.html) (`ppo.py`)\n- [Deep Deterministic Policy Gradient](https://spinningup.openai.com/en/latest/algorithms/ddpg.html) (`ddpg.py`)\n- [Twin Delayed DDPG](https://spinningup.openai.com/en/latest/algorithms/td3.html) (`td3.py`)\n- [Soft Actor-Critic](https://spinningup.openai.com/en/latest/algorithms/sac.html) (`sac.py`)\n- Deep Q-Network (`dqn.py`)\n\n## Implementation Details\n\nNote that implementation details can have a significant effect on performance, as discussed in [What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study](https://arxiv.org/abs/2006.05990). This codebase attempts to be as simple as possible, but note that for instance on-policy algorithms use separate actor and critic networks, a state-independent policy standard deviation, per-minibatch advantage normalisation, and several critic updates per minibatch, while the deterministic off-policy algorithms use layer normalisation. Equally, soft actor-critic uses a transformed Normal distribution by default, but this can also help the on-policy algorithms.\n\n## Results\n\n### Vanilla Policy Gradient/Advantage Actor-Critic\n\n![VPG](results/vpg.png)\n\n### Trust Region Policy Gradient\n\n![TRPO](results/trpo.png)\n\n### Proximal Policy Optimization\n\n![PPO](results/ppo.png)\n\n### Deep Deterministic Policy Gradient\n\n![DDPG](results/ddpg.png)\n\n### Twin Delayed DDPG\n\n![TD3](results/td3.png)\n\n### Soft Actor-Critic\n\n![SAC](results/sac.png)\n\n### Deep Q-Network\n\n![DQN](results/dqn.png)\n\n## Code Links\n\n- [Spinning Up in Deep RL](https://github.com/openai/spinningup) (TensorFlow)\n- [Fired Up in Deep RL](https://github.com/kashif/firedup) (PyTorch)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FKaixhin%2Fspinning-up-basic","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FKaixhin%2Fspinning-up-basic","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FKaixhin%2Fspinning-up-basic/lists"}