-
- [X] I read [the conda-forge documentation](https://conda-forge.org/docs/user/introduction.html#how-can-i-install-packages-from-conda-forge) and could not find the solution for my problem there.
…
-
Hi @keiohta , thanks for sharing such a great project!
I'm wondering if I want to set observation to be image-based using tf2rl, do you have any advice?
-
Hello,
I have a problem when I tried to use DDPG + HER.
The problem seems the definition of observation_space.
```bash
Traceback (most recent call last):
File "/home/all-jy/git/jy_gym_stfl/tr…
-
Thanks for updating this package; very useful!
I am encountering an issue where many of the environments cause my kernel to crash. I am able to run mountain-car and cartpole without issues, but the i…
-
ghost updated
4 years ago
-
I ran SAC with the default config and found that the entropy term was not optimized and it just remained at its start value throughout training.
Does anyone know what could be causing this? Is the…
-
In tianshou.data.collector.py, you note that "Please make sure the given environment has a time limitation.", which troubled me. I wonder how to add it.
In tianshou/test/continuous/test_ppo.py, the…
-
I got the following error while running the excel2csv script (notice that before that I got another error for missing xlrd and I solved it by installing xlrd==0.9.0):
Parsing file: EXIOBASE_convers…
-
I am working with a customized Pendulum-v0 environment which has a maximum timestep attribute to allow early resets and therefore reward tracking and also uses rgb-array's for observation. I am trying…
-
I am trying different RL agents in a custom environment to check their behavior. First I tried PPO2 together with VecFrameStack and everything worked out fine and I got a very reasonable policy. Then …