Deep-Reinforcement-Learning-Algorithms-with-Pytorch
Deep-Reinforcement-Learning-Algorithms-with-Pytorch copied to clipboard
XinJingHao
Clean, Robust, and Unified PyTorch implementation of popular DRL Algorithms (Q-learning, Duel DDQN, PER, C51, Noisy DQN, PPO, DDPG, TD3, SAC, ASL)
Hello, this is the issue for file 2.1. Since I ran the program with the CPU, not CUDA, I changed the default to the CPU in the main dvc, and...
Hi, I'm having problems with action prediction with TD3. The agent tends to predict boundary actions after it starts learning. Do you know what is causing this problem? 
在您这行代码中： https://github.com/XinJingHao/DRL-Pytorch/blob/aa17b796ba632f371863eeaa62406e183177dbae/5.2%20SAC-Continuous/utils.py#L47 为什么对于第一项的dist.log_prob(u)，在dim=1的维度上进行sum操作？按照原来的公式，似乎这一项并不是sum操作吧？ 请您指正！
Metadata
Owner
Metadata
Clean, Robust, and Unified PyTorch implementation of popular DRL Algorithms (Q-learning, Duel DDQN, PER, C51, Noisy DQN, PPO, DDPG, TD3, SAC, ASL)