tianshou
tianshou copied to clipboard
An elegant PyTorch deep reinforcement learning library.
- [ x] I have marked all applicable categories: + [ ] exception-raising bug + [ ] RL algorithm bug + [ ] documentation request (i.e. "X is missing from...
- [ ] I have marked all applicable categories: + [ ] exception-raising bug + [ ] RL algorithm bug + [ ] documentation request (i.e. "X is missing from...
Hi @thu-ml. tianshou looks awesome. I am the author of [Hydra](https://hydra.cc). I think you should definitely check it out. It can probably make your life much easier when dealing with...
- [x] I have marked all applicable categories: + [ ] exception-raising bug + [ ] RL algorithm bug + [ ] documentation request (i.e. "X is missing from the...
Can running and training be separated? For example, we deploy on the cloud, send data to the cloud for training, and issue policies to local hosts intermittently or in real...
- [x] I have marked all applicable categories: + [x] exception-raising bug + [ ] RL algorithm bug + [ ] documentation request (i.e. "X is missing from the documentation.")...
## RL algorithm bug Ratio probability of the action should have been saved for original weights taking this action, it currently re-computes the probability with updated weights which is incorrect....
The bug will cause gradient exploding when add action mask in the dist_fn.
“TypeError: only integer tensors of a single element can be converted to an index” is on line 181 of “test_ppo.py”. End then,I try change ` for epoch, epoch_stat, info in...
- [x] I have marked all applicable categories: + [ ] exception-raising bug + [ ] RL algorithm bug + [ ] documentation request (i.e. "X is missing from the...