{"id":20569937,"url":"https://github.com/zubair-irshad/udacity_deep_rl","last_synced_at":"2026-04-09T16:51:26.032Z","repository":{"id":105045012,"uuid":"262185591","full_name":"zubair-irshad/udacity_deep_rl","owner":"zubair-irshad","description":"My solutions (with explanations) to the Udacity Deep Reinforcement Learning Nano Degree Program assignments, mini-projects and projects","archived":false,"fork":false,"pushed_at":"2020-06-02T17:46:18.000Z","size":10249,"stargazers_count":1,"open_issues_count":0,"forks_count":2,"subscribers_count":4,"default_branch":"master","last_synced_at":"2025-03-06T09:47:40.524Z","etag":null,"topics":["ddpg-algorithm","deep-neural-networks","deep-q-network","deep-reinforcement-learning","dqn","ppo","pytorch","reinforcement-learning","unity-ml-agents"],"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":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/zubair-irshad.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":"2020-05-08T00:08:55.000Z","updated_at":"2024-09-27T22:52:00.000Z","dependencies_parsed_at":null,"dependency_job_id":"c3607f4a-c49d-4321-90cc-00e11b6afe12","html_url":"https://github.com/zubair-irshad/udacity_deep_rl","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/zubair-irshad/udacity_deep_rl","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zubair-irshad%2Fudacity_deep_rl","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zubair-irshad%2Fudacity_deep_rl/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zubair-irshad%2Fudacity_deep_rl/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zubair-irshad%2Fudacity_deep_rl/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/zubair-irshad","download_url":"https://codeload.github.com/zubair-irshad/udacity_deep_rl/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zubair-irshad%2Fudacity_deep_rl/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279004823,"owners_count":26083783,"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":"2025-10-10T02:00:06.843Z","response_time":62,"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":["ddpg-algorithm","deep-neural-networks","deep-q-network","deep-reinforcement-learning","dqn","ppo","pytorch","reinforcement-learning","unity-ml-agents"],"created_at":"2024-11-16T05:09:53.129Z","updated_at":"2025-10-10T17:46:53.273Z","avatar_url":"https://github.com/zubair-irshad.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"My solutions (with explanations) to the Udacity Deep Reinforcement Learning Nano Degree Program\n\nCurrent Progress:\n\nIntroduction to Deep RL\n-----------------------\n\n**Monte Carlo Methods**\n\n- Implementation of [Monteo Carlo Methods](https://web.stanford.edu/class/psych209/Readings/SuttonBartoIPRLBook2ndEd.pdf#page=113) for the enviornment [BlackJack](https://github.com/openai/gym/blob/master/gym/envs/toy_text/blackjack.py)\n\n**Temporal Difference Methods**\n\n- Implementation of [Sarsa](https://web.stanford.edu/class/psych209/Readings/SuttonBartoIPRLBook2ndEd.pdf#page=154), [Q-learning](https://web.stanford.edu/class/psych209/Readings/SuttonBartoIPRLBook2ndEd.pdf#page=157) and [Expected-Sarsa](https://web.stanford.edu/class/psych209/Readings/SuttonBartoIPRLBook2ndEd.pdf#page=157)  for the enviornment [CliffWalking](https://github.com/openai/gym/blob/master/gym/envs/toy_text/cliffwalking.py)\n\nDeep Value Iterations\n-----------------------\n\n**Deep Q Network - DQN**\n\n- Implementation of [Deep Q Network](https://arxiv.org/abs/1312.5602) for the enviornment [Lunar Lander](https://gym.openai.com/envs/LunarLander-v2/)\n\n\nProject1: Navigation\n-----------------------\n- Implemented [Deep Q Network](https://arxiv.org/abs/1312.5602) to navigate an agent inside an enviornment while avoiding obstacle(bad reward paths)\n\n\nPolicy Gradients\n-----------------------\n\n**REINFORCE**\n\n- Implementation of [REINOFRCE Algorithm](https://papers.nips.cc/paper/1713-policy-gradient-methods-for-reinforcement-learning-with-function-approximation.pdf) to teach an agent to play [Pong from scratch](https://gym.openai.com/envs/Pong-v0/)\n\n**Proximal Policy Optimizaiton**\n\n- Implementation of [PPO Algorithm](https://openai.com/blog/openai-baselines-ppo/) to teach an agent to play [Pong from scratch](https://gym.openai.com/envs/Pong-v0/)\n\n\nProject2: Continuous Control\n-----------------------\n- Implemented [Deep Deterministic Policy Gradients](https://spinningup.openai.com/en/latest/algorithms/ddpg.html) to teach an 2-DOF robotic manipulator to reach a goal location. Enviornment used for training and testing: [Reacher](https://github.com/Unity-Technologies/ml-agents/blob/master/docs/Learning-Environment-Examples.md#reacher)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzubair-irshad%2Fudacity_deep_rl","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzubair-irshad%2Fudacity_deep_rl","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzubair-irshad%2Fudacity_deep_rl/lists"}