Michal Gregor
Michal Gregor
* Added an additional argument to fit in core.py, which allows stopping by the number of episodes. * Arguments nb_steps and nb_max_episode_steps are both optional now, but at least one...
This PR adds a policy very closely modelled on the LinearAnnealedPolicy, but with exponential decay instead of a linear schedule.
Hi, I've been running some of the experiment scripts provided with the package and I am getting weirdly bad results – mostly there is just no visible improvement at all....
- [X] I have marked all applicable categories: - [X] I have visited the [source website](https://github.com/thu-ml/tianshou/) - [X] I have searched through the [issue tracker](https://github.com/thu-ml/tianshou/issues) for duplicates - [X] I...
Hi, it seems that the current version of RLlib does not support environment rendering – since the gym/gymnasium package changed and there is no longer a rendering module under classic_control...
Hi! I've noticed that the TTS plugin stops reading once I switch to another app or lock the screen. This is not very good as those seem to be the...