Alexander Nikulin
Alexander Nikulin
## Description Implementation of new algorithm - APO. See https://github.com/vwxyzjn/cleanrl/issues/210. Work in progress. ## Types of changes - [ ] Bug fix - [ ] New feature - [x] New...
## Description Closes #198 ## Types of changes - [ ] Bug fix - [x] New feature - [ ] New algorithm - [ ] Documentation ## Checklist: - [x]...
Although it is now common to solve most problems using discounted reward, this does not always correspond to the real problem (not episodic, long-horizon), where it is important to use...
Hi! I'm a bit puzzled as to how a timeout could be handled correctly in your implementation of PPO (well, this is relevant for all variants). I am especially surprised...
Hi! I want to visualize my agent's rollouts. However, the resulting videos turns out to be strange, I see some color artifacts. Should it be like this? What I do:...
## Describe the bug Can not create MiniGrid environments. ## To Reproduce ```python import envpool envpool.make("MiniGrid-Empty-5x5-v0", env_type="gym") ``` ## System info ```python import envpool, numpy, sys print(envpool.__version__, numpy.__version__, sys.version, sys.platform)...
### Question While hdf5 and h5py is the most popular approach for multi-dimensional arrays storage, is has some major limitations. For example, the inability to read data in multiple processes...
### Is your feature request related to a problem? Please describe Hi, I'm currently developing a library with environments for meta-RL research. In order not to reinvent the wheel, I...
first iteration of Minari integration, see https://github.com/tinkoff-ai/CORL/issues/66
There we will track out progress for [Minari](https://github.com/Farama-Foundation/Minari) integration with CORL. Minari is a standard format for offline RL datasets, with popular reference datasets and related utilities, which we believe...