1. 相关论文:Human-level control through deep reinforcement learning
CODE链接(需翻墙) 另外的链接(不需要翻墙):kuz/DeepMind-Atari-Deep-Q-Learner
实现的算法名称:Deep Q-Networks(DQN)
推荐指数(★★★★★)
推荐理由:谷歌公司开源的第一个深度强化学习软件包,重要价值不用我多说了吧。
2. 软件包名称:ehrenbrav/DeepQNetwork
实现算法:DQN 应用场景:玩超级马里奥游戏 推荐指数(★★★)
相关论文:Human-Level Control through Deep Reinforcement Learning
实现算法: DQN, persistent advantage learning, dueling network, double DQN, A3C
推荐指数(★★★★)
4. 软件包名称:iassael/learning-to-communicate
实现算法:Reinforced Inter-Agent Learning (RIAL) and Differentiable Inter-Agent Learning (DIAL)
推荐指数(★★★)
相关论文:[1605.06676] Learning to Communicate with Deep Multi-Agent Reinforcement Learning
推荐指数(★★★) 推荐理由:Simple environment for creating very simple 2D games and training neural network models to perform tasks within them
相关论文:A Sandbox for Learning from Games
6. 软件包名称:eparisotto/ActorMimic
推荐指数(★★★) 实现算法:ActorMimic
相关论文:Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning
1. 软件包名称:devsisters/DQN-tensorflow
实现算法:DQN
推荐指数(★★★)
相关论文:Human-Level Control through Deep Reinforcement Learning
2. 软件包名称:gliese581gg/DQN_tensorflow
实现算法:DQN
推荐指数(★★)
3. 软件包名称:nivwusquorum/tensorflow-deepq
实现算法:DQN
推荐指数(★★★★)
推荐理由:可以用Jupyter Notebook
4. 软件包名称: deep-rl-tensorflow
实现算法:DQN、DDQN、Dueling Network
相关论文:
[1] Playing Atari with Deep Reinforcement Learning
[2] Human-Level Control through Deep Reinforcement Learning
[3] Deep Reinforcement Learning with Double Q-learning
[4] Dueling Network Architectures for Deep Reinforcement Learning
推荐指数(★★★★★) 推荐理由:基于TensorFlow下的多种DRL算法实现,有很好的扩展价值。
5. 软件包名称:coreylynch/async-rl
实现算法:A3C 推荐指数(★★★★)
相关论文:Asynchronous Methods for Deep Reinforcement Learning".
推荐理由:结合使用Tensorflow + Keras + OpenAI Gym
1. 软件包名称:matthiasplappert/keras-rl
实现算法:
相关论文在标注链接里面。
推荐指数(★★★★★)
推荐理由:基于keras的最好的一款DRL软件包,实现的算法较全(包括离散动作空间、连续动作空间)
实现算法:DQN
推荐指数(★★★)
推荐理由:基于Theano框架
1. 软件包名称:tambetm/simple_dqn
实现算法:DQN
相关论文:Human-Level Control through Deep Reinforcement Learning
推荐指数(★★)
主要实现算法:DQN,prioritized experience replay, double Q-learning, DDPG
推荐指数(★★★)
实现算法: A3C 推荐指数(★★)
相关论文:Asynchronous Methods for Deep Reinforcement Learning.
3. 软件包名称:miyosuda/async_deep_reinforce
实现算法: A3C
推荐指数(★★)
相关论文:Asynchronous Methods for Deep Reinforcement Learning.
实现算法:
推荐指数(★★★★★)
推荐理由:OpenAI出品,必是精品。
推荐指数(★★★★★)
推荐理由:OpenAI Gym is a toolkit for developing and comparing reinforcement learning algorithms.
推荐指数(★★★★★)
推荐理由:A software platform for measuring and training an AI's general intelligence across the world's supply of games, websites and other applications.(多么美好的未来啊)
7. 软件包名称:joschu/modular_rl
实现算法: TRPO,Proximal Policy Optimization,CEM
推荐指数(★★★)
实现算法:Variational Information Maximizing Exploration (VIME)
推荐指数(★★)
相关论文:VIME: Variational Information Maximizing Exploration
1. 相关论文:Human-level control through deep reinforcement learning
CODE链接 实现算法:DQN
推荐指数(★★★★)
推荐理由:首次基于Caffe深度学习框架尝试解决深度强化学习问题。
2. 软件包名称:Replicating-DeepMind
主要实现算法:DQN
推荐指数(★★)
3. 软件包名称:xbpeng/DeepTerrainRL
相关论文: Terrain-Adaptive Locomotion Skills Using Deep Reinforcement Learning
推荐指数(★★)
推荐指数(★★★★★)
推荐理由:A customisable 3D platform for agent-based AI research(用来对抗OpenAI的Universe?)
5. 软件包名称:junhyukoh/nips2015-action-conditional-video-prediction
推荐指数(★★)
相关论文:Action-Conditional Video Prediction using Deep Networks in Atari Games
实现算法:DRQN (Recurrent DQN)
推荐指数(★★★)
相关论文:Deep Recurrent Q-Learning for Partially Observable MDPs
1. 软件包名称:karpathy/reinforcejs
实现算法:
推荐指数(★★★★)
推荐理由:单凭Javascript,我就觉得很牛逼了。
1. 软件包名称:deeplearning4j/rl4j
实现算法: DQN,A3C
推荐指数(★★★★★)
推荐理由:Java语言,我的最爱。目前商用价值最高的语言。
1. 软件包名称:yenchenlin/DeepLearningFlappyBird 和 songrotek/DRL-FlappyBird
实现算法:DQN
应用场景:玩愤怒的小鸟
推荐指数(★★★★)
2. 软件包名称:bitwise-ben/Snake
实现算法:DQN
应用场景:玩贪吃蛇
推荐指数(★★★)
3. 软件包名称:yanpanlau/DDPG-Keras-Torcs
实现算法:DDPG
基于的框架:keras
应用场景:TORCS赛车
相关论文:Deep Deterministic Policy Gradient
推荐指数(★★★★★) 推荐理由:男生应该都对车有兴趣吧
实现算法:DSR
应用场景:Doom射击
推荐指数(★★★★)
相关论文:Deep Successor Reinforcement Learning (DSR)
两年期间,又有许多有价值的强化学习项目在网上开源:
简述:Python replication for Sutton & Barto's bookReinforcement Learning: An Introduction (2nd Edition)
2. dennybritz/reinforcement-learning
简述:Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.
3. MorvanZhou/Reinforcement-learning-with-tensorflow
简述:Simple Reinforcement learning tutorials,适合入门。
简述:TRFL (pronounced "truffle") is a library built on top of TensorFlow that exposes several useful building blocks for implementing Reinforcement Learning agents.
简述:Deep Learning and Reinforcement Learning Library for Scientists
简述:OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
简述:Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.
简述:Deep Reinforcement Learningfor Keras.
简述:a TensorFlow library for applied reinforcement learning
简述:rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.
11. NervanaSystems/coach
简述:Reinforcement Learning Coach by Intel AI Lab enables easy experimentation with state of the art Reinforcement Learning algorithms
12. tensorflow/agents
简述:TF-Agents is a library for Reinforcement Learning in TensorFlow