{"id":15952838,"url":"https://github.com/jedrazb/rl-grid-world","last_synced_at":"2026-04-29T17:32:11.981Z","repository":{"id":113654263,"uuid":"232642908","full_name":"jedrazb/rl-grid-world","owner":"jedrazb","description":"Reinforcement learning agent which finds a path to the goal in a grid world. This exercise was done as a coursework for course C424 at Imperial College London.","archived":false,"fork":false,"pushed_at":"2020-01-08T20:13:55.000Z","size":13,"stargazers_count":3,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-02-09T18:49:41.747Z","etag":null,"topics":["deep-q-learning","deep-q-network","grid-world","reinforcement-agents","reinforcement-learning","reinforcement-learning-agent"],"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/jedrazb.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":"2020-01-08T19:34:24.000Z","updated_at":"2024-10-15T00:44:17.000Z","dependencies_parsed_at":null,"dependency_job_id":"aa16fd6f-3428-4146-88bf-2b30bc913b41","html_url":"https://github.com/jedrazb/rl-grid-world","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/jedrazb%2Frl-grid-world","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jedrazb%2Frl-grid-world/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jedrazb%2Frl-grid-world/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jedrazb%2Frl-grid-world/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jedrazb","download_url":"https://codeload.github.com/jedrazb/rl-grid-world/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247142042,"owners_count":20890652,"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-q-learning","deep-q-network","grid-world","reinforcement-agents","reinforcement-learning","reinforcement-learning-agent"],"created_at":"2024-10-07T13:09:57.687Z","updated_at":"2026-04-29T17:32:11.949Z","avatar_url":"https://github.com/jedrazb.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Deep Q-learning agent in the grid world\nDeep Q-learning agent which finds a path to the goal in a grid world. This exercise was done as a coursework for course C424 at Imperial College London.\n\n\u003cp align=\"center\"\u003e\u003cimg src=\"https://media.giphy.com/media/fAo4EH4rFJO7xPjKyS/giphy.gif\" width=\"400\"\u003e\u003c/p\u003e\n\n--------\nDependencies: `numpy`, `cv2`, `torch`\n\nTo start the training run:\n```\npython train_and_test.py\n```\n\n-------\n\nFollowing techniques were used:\n* Deep Q-network (created in PyTorch)\n* Models with continous (`agent_radians.py`) and discrete actions (`agent.py`)\n* Prioritised experience replay buffer\n* Epsilon greedy policy\n* Target network\n* Sampling using Cross Entropy Method\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjedrazb%2Frl-grid-world","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjedrazb%2Frl-grid-world","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjedrazb%2Frl-grid-world/lists"}