{"id":21022559,"url":"https://github.com/alro10/rl_pong","last_synced_at":"2026-04-25T15:35:11.044Z","repository":{"id":121033162,"uuid":"137114937","full_name":"Alro10/RL_Pong","owner":"Alro10","description":"This is a repository for project in MO810 course-1s2018 IC-UNICAMP. The project is about implement DQN, ES and policy gradients for Pong and Catch game.","archived":false,"fork":false,"pushed_at":"2018-06-19T20:44:09.000Z","size":187,"stargazers_count":0,"open_issues_count":0,"forks_count":1,"subscribers_count":0,"default_branch":"master","last_synced_at":"2025-12-31T01:58:47.258Z","etag":null,"topics":["catch","deep-reinforcement-learning","dqn","google-colab","google-colaboratory","pong-game"],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","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/Alro10.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2018-06-12T18:55:22.000Z","updated_at":"2018-06-19T20:44:10.000Z","dependencies_parsed_at":null,"dependency_job_id":"d3a3c4b2-05e3-427e-909a-31d667970e2b","html_url":"https://github.com/Alro10/RL_Pong","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Alro10/RL_Pong","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Alro10%2FRL_Pong","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Alro10%2FRL_Pong/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Alro10%2FRL_Pong/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Alro10%2FRL_Pong/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Alro10","download_url":"https://codeload.github.com/Alro10/RL_Pong/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Alro10%2FRL_Pong/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32267710,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-25T09:15:33.318Z","status":"ssl_error","status_checked_at":"2026-04-25T09:15:31.997Z","response_time":59,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["catch","deep-reinforcement-learning","dqn","google-colab","google-colaboratory","pong-game"],"created_at":"2024-11-19T11:12:46.906Z","updated_at":"2026-04-25T15:35:11.013Z","avatar_url":"https://github.com/Alro10.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# DQN-NES-Pong\nThis is a repository for project in MO810 course-1s2018 IC-UNICAMP. The project is about implement DQN, NES and policy gradients for Pong and Catch game.\n\u003cbr /\u003e\n\n## Requirements\n\nPython 3.5, PyTorch \u003e= 0.2.0, numpy, gym, universe, cv2.\n\u003cbr /\u003e\n\n\n## Deep Q-learning (DQN):\n\n* `dqn_pong.ipynb` : This is a DQN implementation for Pong game (gym environment) and was trained in google colab (aprox 5 hours). Achieved **reward = 18**.\n\n* `kerasdqn_catch.ipynb`: For learn more about DQN, I decided to implement a shallow neural network for catch enviroment. See the results in file.\n\u003cbr /\u003e\n\n## Evolution Strategies (Natural):\n\n* `main.py` : Train ES on Pong and achieved **reward = 5** after 72 hours of training. Functions from `train.py`, `envs.py` , `model.py`\n\n```\npython3 main.py --env-name Pong-v4 --n 10 --lr 0.01 --useAdam\n```\n\n* `catch_ES.ipynb`: NES implementation for catch game! See results in flie. \n\u003cbr /\u003e\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falro10%2Frl_pong","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Falro10%2Frl_pong","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falro10%2Frl_pong/lists"}