autonomous-learning-library
autonomous-learning-library copied to clipboard
cpnota
A PyTorch library for building deep reinforcement learning agents.
I'm sorting out an odd error in the time feature body related to the PPO mujuco thing. However, there's no documentation in the code or documentation on what specific bodies...
@cpnota you may want to read through the imports in the files in the scripts folder. I'm pretty sure a decent number are unnecessary.
The tests depend on the [torch-torching](https://pypi.org/project/torch-testing/) library. It appears that this is not being maintained, so it would be good to refactor this tests such that the dependency can be...
https://github.com/cpnota/autonomous-learning-library/blob/3ec67d5c05c521344bbba47045c1b179a8ccc275/all/experiments/run_experiment.py#L5-L13 `run_experiment` should only take `agents`, `envs` and `experiment`. Then we could call it like this: ```python3 def make_experiment(agent, env): return CustomExperiment( agent, env, render=False, quiet=False, write_loss=True # Allows for...
Currently the experiment runner first runs the training, then the testing. However, often it is interesting to get intermediate test results while training. E.g. run (and log) a test episode...
Hi Chris, Do you plan to add an EnvRunner class supporting multiprocess?
The documentation is a little out of date and needs to be updated and rebuilt.
Pytorch's implementation of `add_hparams` isn't really quite correctly. In particular, it creates a new events file for every write, which is not quite what we want. We should write our...
We are sticking with Tensorboard for Logging. However, we want to make sure that people can easily write and inject their own Loggers. We need to make sure our interface...