I have implemented DDPG in PyTorch for continuous action reinforcement learning and tested it on OpenAI envs like Pendulum-v0 and BiPedal Walker - v2. Have a look and feel free to ask any doubts, if you have. Hope it helps anyone who is stuck at these problems.
Hey there. Just tried running your software. Hit an error right out of the gate. What versions of Python and PyTorch did you use?
Hello. I got it to work. Let me know what version of PyTorch you wrote this for. If my fixes were for a newer version, I’ll send you a pull request.