Costa Huang
Costa Huang
Hi @wookayin, I have been using the `expt` package to do plotting, and the experience has been great. Any chance you could add support for plotting the **median**? I am...
Hi Jongwook, Per our earlier discussion, here is the repository for Open RL Benchmark https://github.com/openrlbenchmark/openrlbenchmark. We now have tracked experiments from a pretty impressive collection of RL libraries such as...
现在 `cloudbase framework deploy` 有些时候花的时间很长，我们有个maven项目花了10分钟build… 有没有可能加个选项类似 `cloudbase framework deploy —no-wait` 直接返回如果提交部署没有错误，而不是一直block到部署成功呢？
## Problem Description A much requested inclusion in the library is to add unit tests. Among other things, "the key benefit of unit tests is to make sure the logic...
`rnd_ppo.py` is a bit dated, and I recommend refactoring it to match other PPO style, which would include: - [x] change the name from `rnd_ppo.py` to `ppo_rnd.py` - [x] use...
## Problem Description Pytorch recently announced a universal job launcher called torchx (https://pytorch.org/torchx/latest/), which supports launching jobs at AWS batch, docker, k8s, and more. We should adopt `torchx`, which perfectly...
As CleanRL gets more mature, it's time to re-think the future. With CleanRL 1.0, we'd hope to further improve documentation and design better contribution guidelines. This issue tracks a few...
## Description This PR adds a first pass of hyperparameter optimization. The API design roughly looks like ```python import optuna from cleanrl_utils.tuner import Tuner tuner = Tuner( script="cleanrl/ppo.py", metric="charts/episodic_return", metric_last_n_average_window=50,...
## Problem Description Dealing with `poetry lock` is no fun. When you have thousands of dependencies, `poetry lock` could take 5-10 hours. #235 #236 use CI servers to help with...
## Description ## Types of changes - [ ] Bug fix - [x] New feature ## Checklist: - [ ] I've read the [CONTRIBUTION](https://github.com/vwxyzjn/cleanrl/blob/master/CONTRIBUTING.md) guide (**required**). - [ ] I...