noreward-rl:[ICML 2017] TensorFlow代码,用于好奇心驱动的深度强化学习探索

上传者: 42116705 | 上传时间: 2022-05-30 14:48:41 | 文件大小: 2.04MB | 文件类型: ZIP
自我监督预测的好奇心驱动探索 在ICML 2017中 , , ,加州大学伯克利分校 这是我们基于ICLS 基于张量流的实现,该。 当来自环境的外部奖励稀疏时,想法是用内在的基于好奇心的动机(ICM)来培训代理商。 令人惊讶的是,即使环境中没有可用的奖励,您也可以使用ICM,在这种情况下,代理仅出于好奇而学会探索:“没有奖励的RL”。 如果您发现这项工作对您的研究有用,请引用: @inproceedings{pathakICMl17curiosity, Author = {Pathak, Deepak and Agrawal, Pulkit and Ef

文件下载

资源详情

[{"title":"( 29 个子文件 2.04MB ) noreward-rl:[ICML 2017] TensorFlow代码,用于好奇心驱动的深度强化学习探索","children":[{"title":"noreward-rl-master","children":[{"title":".gitignore <span style='color:#111;'> 113B </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 3.54KB </span>","children":null,"spread":false},{"title":"doomFiles","children":[{"title":"doom_my_way_home_sparse.py <span style='color:#111;'> 4.39KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 461B </span>","children":null,"spread":false},{"title":"action_space.py <span style='color:#111;'> 6.04KB </span>","children":null,"spread":false},{"title":"wads","children":[{"title":"my_way_home_sparse.wad <span style='color:#111;'> 28.35KB </span>","children":null,"spread":false},{"title":"my_way_home_dense.wad <span style='color:#111;'> 28.22KB </span>","children":null,"spread":false},{"title":"my_way_home_verySparse.wad <span style='color:#111;'> 28.34KB </span>","children":null,"spread":false}],"spread":true},{"title":"__init__.py <span style='color:#111;'> 12.03KB </span>","children":null,"spread":false},{"title":"doom_env.py <span style='color:#111;'> 20.84KB </span>","children":null,"spread":false},{"title":"doom_my_way_home_verySparse.py <span style='color:#111;'> 4.40KB </span>","children":null,"spread":false}],"spread":true},{"title":"LICENSE <span style='color:#111;'> 2.57KB </span>","children":null,"spread":false},{"title":"models","children":[{"title":"download_models.sh <span style='color:#111;'> 899B </span>","children":null,"spread":false}],"spread":true},{"title":"src","children":[{"title":".gitignore <span style='color:#111;'> 1.06KB </span>","children":null,"spread":false},{"title":"mario.py <span style='color:#111;'> 1.48KB </span>","children":null,"spread":false},{"title":"env_wrapper.py <span style='color:#111;'> 6.76KB </span>","children":null,"spread":false},{"title":"train.py <span style='color:#111;'> 7.62KB </span>","children":null,"spread":false},{"title":"inference.py <span style='color:#111;'> 10.53KB </span>","children":null,"spread":false},{"title":"constants.py <span style='color:#111;'> 1.52KB </span>","children":null,"spread":false},{"title":"worker.py <span style='color:#111;'> 8.63KB </span>","children":null,"spread":false},{"title":"utils.py <span style='color:#111;'> 348B </span>","children":null,"spread":false},{"title":"model.py <span style='color:#111;'> 16.68KB </span>","children":null,"spread":false},{"title":"requirements.txt <span style='color:#111;'> 1.13KB </span>","children":null,"spread":false},{"title":"a3c.py <span style='color:#111;'> 20.38KB </span>","children":null,"spread":false},{"title":"demo.py <span style='color:#111;'> 4.81KB </span>","children":null,"spread":false},{"title":"envs.py <span style='color:#111;'> 15.46KB </span>","children":null,"spread":false}],"spread":false},{"title":"images","children":[{"title":"mario2.gif <span style='color:#111;'> 711.53KB </span>","children":null,"spread":false},{"title":"vizdoom.gif <span style='color:#111;'> 621.50KB </span>","children":null,"spread":false},{"title":"mario1.gif <span style='color:#111;'> 716.86KB </span>","children":null,"spread":false}],"spread":true}],"spread":true}],"spread":true}]

评论信息

免责申明

【只为小站】的资源来自网友分享,仅供学习研究,请务必在下载后24小时内给予删除,不得用于其他任何用途,否则后果自负。基于互联网的特殊性,【只为小站】 无法对用户传输的作品、信息、内容的权属或合法性、合规性、真实性、科学性、完整权、有效性等进行实质审查;无论 【只为小站】 经营者是否已进行审查,用户均应自行承担因其传输的作品、信息、内容而可能或已经产生的侵权或权属纠纷等法律责任。
本站所有资源不代表本站的观点或立场,基于网友分享,根据中国法律《信息网络传播权保护条例》第二十二条之规定,若资源存在侵权或相关问题请联系本站客服人员,zhiweidada#qq.com,请把#换成@,本站将给予最大的支持与配合,做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明