{"id":19622303,"url":"https://github.com/camigord/distributed_ddpg","last_synced_at":"2025-04-28T03:32:33.516Z","repository":{"id":253787509,"uuid":"102470921","full_name":"camigord/Distributed_DDPG","owner":"camigord","description":"Parallel implementation of DDPG","archived":false,"fork":false,"pushed_at":"2017-09-06T14:58:20.000Z","size":6705,"stargazers_count":14,"open_issues_count":0,"forks_count":3,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-04-05T06:11:28.971Z","etag":null,"topics":["ddpg","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":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/camigord.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":"2017-09-05T11:03:55.000Z","updated_at":"2024-12-22T01:43:06.000Z","dependencies_parsed_at":"2024-08-19T14:59:36.346Z","dependency_job_id":"7dd25a30-75a4-4278-88e9-adaac7722663","html_url":"https://github.com/camigord/Distributed_DDPG","commit_stats":null,"previous_names":["camigord/distributed_ddpg"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/camigord%2FDistributed_DDPG","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/camigord%2FDistributed_DDPG/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/camigord%2FDistributed_DDPG/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/camigord%2FDistributed_DDPG/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/camigord","download_url":"https://codeload.github.com/camigord/Distributed_DDPG/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251246394,"owners_count":21558762,"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":["ddpg","deep-reinforcement-learning"],"created_at":"2024-11-11T11:27:06.815Z","updated_at":"2025-04-28T03:32:28.508Z","avatar_url":"https://github.com/camigord.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Distributed-DDPG\n\n\n\n## Overview\n\nThe purpose of this repository is to implement the Deep Deterministic Policy Gradient algorithm or [DDPG](https://arxiv.org/abs/1509.02971) in a distributed fashion as proposed [here](https://arxiv.org/abs/1704.03073).\n\nI will start by evaluating the performance of DDPG in simple cases and then comparing this performance when distributing the training process among several \"workers\".\n\n## MountainCarContinuous-v0 (OpenAI)\n\n\u003ctable\u003e\n  \u003ctr\u003e\n    \u003ctd\u003e\u003cimg src=\"./assets/MountainCar.gif?raw=true\" width=\"400\"\u003e\u003c/td\u003e\n  \u003c/tr\u003e\n\u003c/table\u003e\n\nI evaluated the performance of the standard DDPG approach on the [MountainCarContinuous](https://github.com/openai/gym/wiki/MountainCarContinuous-v0) task. The figure below shows the training curves until the problem is considered solved.\n\n\u003cimg src=\"./assets/tensorboard.jpg\"\u003e\n\nThe provided results were obtained by running a single worker. To replicate the results run the following commands in two different consoles:\n\n  ```\n  # Parameter server\n  python ddpg.py --job_name=\"ps\" --task_index=0\n  ```\n\n  ```\n  # First worker\n  python ddpg.py --job_name=\"worker\" --task_index=0\n  ```\n\n  To visualize the training process using TensorBoard:\n\n  ```\n  # TensorBoard\n  tensorboard --logdir=results/tboard_ddpg/\n  ```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcamigord%2Fdistributed_ddpg","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcamigord%2Fdistributed_ddpg","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcamigord%2Fdistributed_ddpg/lists"}