-
when I installed pytorch-rl on py3.6, I only have ddpg and ddqn.
-
Excuse me, I have some questions:
First, I see that you are using PyTorch and what version of PyTorch framework you are using.
Second, compared with the program of DQN, does this DDPG use different …
-
### What happened + What you expected to happen
### Training Rllib-DDPG with custom environment leads error in Inference.
When I feed numpy float32 array to my trained policy (DDPG) with 'comput…
-
Hi,
I managed to run examples/tf/her_ddpg_fetchreach.py with tuned parameters (PR #1739 ). Then I try using pytorch, and something strange happens. It was working fine at first then crashes dramati…
-
目前在文档中看到本项目实现了非常丰富的智能体模型算法，以及不同类型Env的适配，但是好像具体的benchmark试验结果汇总比较有限，存在大量的结果缺失，例如[Atari](https://xuance.readthedocs.io/zh/latest/documents/benchmark/atari.html)、MPE、MAgent等均无试验结果展示，仅有的Mujoco试验结果也不是很完整，仅…
-
Hi Guan-Horng,
Thanks for your great implementation! I am wondering why do we append additional (s a r) pair to the replay buffer after one episode is done? The reward in that pair is zero, I think…
-
Attempting the spinning up tutorial using windows and wsl2 by following the link given in the installation tutorial.
After setting up conda and wsl2, I made my conda environment, then followed the …
-
- Value based RL
- [ ] DQN
- [ ] Rainbow DQN
- [ ] [CQL](https://sites.google.com/view/cql-offline-rl)
- Value based + Policy based RL
- [x] DDPG
- [ ] [TD3](https://spinni…
-
See https://github.com/pytorch/pytorch/issues/975 for more info
PyTorch TRPO appears 50% slower than TF. Not sure about PPO, but I expect the wall-clock time gap will be the same.
To fix this is…
-
### Search before asking
- [X] I searched the [issues](https://github.com/ray-project/ray/issues) and found no similar issues.
### Ray Component
RLlib
### What happened + What you expect…