搜索资源列表
DQN
- 谷歌DeepMind2015年2月发表的人工智能算法,可以在雅达利2600游戏机的49个游戏中击败人类专业玩家-human-level control through RL
dqn
- 简单程序,很能说明DQN的运行方式,通过深度网络和Qlearning的结合,训练使得最后小球能移动到最左边(Simple procedures, it can explain the way of DQN, through the combination of deep network and Qlearning, so that the last ball can move to the left.)
RL
- 强化学习 DQN代码,和通信相关,利用python进行训练,大家可以看看(reinforcement learning)
pytorch-a2c-ppo-acktr-master
- 改代码为ACKTR代码,该算法比传统的TRPO和DQN在运行速度和计算量都有很大的提升(scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation)
C51-DDQN-Keras-master
- C51-DDQN-Keras-master 分类版DDQN机器学习Demo代码(C51-DDQN-Keras-master DDQN reinfocrement learning)
Proximal_Policy_Optimization
- 强化学习可以按照方法学习策略来划分成基于值和基于策略两种。而在深度强化学习领域将深度学习与基于值的Q-Learning算法相结合产生了DQN算法,通过经验回放池与目标网络成功的将深度学习算法引入了强化学习算法。(Reinforcement learning can be divided into value-based learning and strategy based learning according to method learning strategies. In the fiel