{"id":15468995,"url":"https://github.com/ajaysub110/rlin200lines","last_synced_at":"2025-11-17T13:39:51.725Z","repository":{"id":113986122,"uuid":"182436391","full_name":"ajaysub110/RLin200Lines","owner":"ajaysub110","description":"PyTorch implementations of Reinforcement Learning algorithms in less than 200 lines","archived":false,"fork":false,"pushed_at":"2020-04-03T14:00:58.000Z","size":3120,"stargazers_count":10,"open_issues_count":0,"forks_count":2,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-08-01T07:12:10.686Z","etag":null,"topics":["deep-reinforcement-learning","dqn","machine-learning","policy-gradient","ppo","pytorch-implementations","reinforcement-learning","reinforcement-learning-algorithms","soft-actor-critic"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ajaysub110.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2019-04-20T17:40:21.000Z","updated_at":"2022-12-07T05:27:46.000Z","dependencies_parsed_at":null,"dependency_job_id":"762a66c2-fd7d-4a80-8694-10b90514b8e4","html_url":"https://github.com/ajaysub110/RLin200Lines","commit_stats":{"total_commits":49,"total_committers":1,"mean_commits":49.0,"dds":0.0,"last_synced_commit":"4e1080cd32d8a4096a98036aa9d081528f7cfb51"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ajaysub110/RLin200Lines","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ajaysub110%2FRLin200Lines","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ajaysub110%2FRLin200Lines/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ajaysub110%2FRLin200Lines/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ajaysub110%2FRLin200Lines/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ajaysub110","download_url":"https://codeload.github.com/ajaysub110/RLin200Lines/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ajaysub110%2FRLin200Lines/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":284893574,"owners_count":27080531,"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","status":"online","status_checked_at":"2025-11-17T02:00:06.431Z","response_time":55,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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-reinforcement-learning","dqn","machine-learning","policy-gradient","ppo","pytorch-implementations","reinforcement-learning","reinforcement-learning-algorithms","soft-actor-critic"],"created_at":"2024-10-02T01:48:40.136Z","updated_at":"2025-11-17T13:39:51.701Z","avatar_url":"https://github.com/ajaysub110.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# RL in 200 Lines\nPyTorch implementations of Reinforcement Learning algorithms in less than 200 lines.\n\n## Algorithms:\n\n1. **Deep Reinforcement Learning**\n    - DQN\n    - Soft Actor-Critic (SAC) [[Results]](https://drive.google.com/open?id=1rrzC4DigBsKWXv9YVmV0jI1vhstnwFKd)\n    - Vanilla Policy Gradient (Actor-Critic) [[Results]](https://drive.google.com/open?id=1T9rqRIfZcCe61h2Ib-Q9Fyf2A-B9th2A)\n    - Proximal Policy Optimization (PPO) [[Results]](https://drive.google.com/open?id=1zb6bt5RSZUnCTRw8crWPypXHkiECyRG4)\n    - Deep Deterministic Policy Gradient (DDPG) [[Results]](https://drive.google.com/open?id=1IS06f5od8-mNvi9oaSlIOqFZoxJpdNcx)\n\n2. **Bandits**\n    - Epsilon Greedy\n    - Softmax action selection\n    - UCB-1\n    - REINFORCE\n\n3. **Classical MDP Control**\n    - SARSA\n    - Q-learning\n    - SARSA(lambda)\n    - Vanilla Policy Gradient\n\n4. **Additional Resources**\n    - Report on Bandit algorithms\n    - Report on Classical MDP control algorithms\n    - Contour environment - *gym-contour* \n    - Puddle world - *gym-puddle*\n\n## Dependencies\n- PyTorch\n- Tensorboard\n- OpenAI Gym\n- Numpy\n\n## Usage\n- Clone the repository.\n- Run experiments on an algorithm by running either \u003cname\u003e.py or main.py within its directory.\n- Tensorboard of my experiments can be viewed by using the 'Result' links given above.\n\n## References\n\n- **Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor**, (2018) [[bib]](./bibtex.bib#L9-L15)  by *Tuomas Haarnoja, Aurick Zhou, Pieter Abbeel and Sergey Levine*\n\n- **Proximal Policy Optimization Algorithms**, (2017) [[bib]](./bibtex.bib#L25-L31)  by *John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford and Oleg Klimov*\n\n- **Benchmarking Deep Reinforcement Learning for Continuous Control**, (2016) [[bib]](./bibtex.bib#L17-L23)  by *Yan Duan, Xi Chen, Rein Houthooft, John Schulman and Pieter Abbeel*\n\n- **Playing Atari with Deep Reinforcement Learning**, (2013) [[bib]](./bibtex.bib#L1-L7)  by *Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra and Martin A. Riedmiller*\n\n- **Using Confidence Bounds for Exploitation-Exploration Trade-offs**, (2002) [[bib]](./bibtex.bib#L42-L49)  by *Peter Auer*\n\n- **Eligibility Traces for Off-Policy Policy Evaluation**, (2000) [[bib]](./bibtex.bib#L60-L65)  by *Doina Precup, Richard S. Sutton and Satinder P. Singh*\n\n- **Policy Gradient Methods for Reinforcement Learning with Function Approximation**, (1999) [[bib]](./bibtex.bib#L67-L72)  by *Richard S. Sutton, David A. McAllester, Satinder P. Singh and Yishay Mansour*\n\n- **Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning**, (1992) [[bib]](./bibtex.bib#L33-L40)  by *Ronald J. Williams*\n\n- **Q-learning**, (1992) [[bib]](./bibtex.bib#L51-L58)  by *Chris Watkins and Peter Dayan*\n\n- **Deterministic Policy Gradient Algorithms**, (2014) [[bib]](../bibtex.bib#L74-L79)  by *David Silver, Guy Lever, Nicolas Manfred Otto Heess, Thomas Degris, Daan Wierstra and Martin A. Riedmiller*","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fajaysub110%2Frlin200lines","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fajaysub110%2Frlin200lines","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fajaysub110%2Frlin200lines/lists"}