garage
garage copied to clipboard
A toolkit for reproducible reinforcement learning research.
I have been trying to install Garage by: pip install --user garage And I get this error: Installing collected packages: torch Attempting uninstall: torch Found existing installation: torch 1.10.0 Uninstalling...
Hi, I have two issues that I do not quite understand why they are part of the code 1. The code overwrites the action `a` in the deterministic case: https://github.com/rlworkgroup/garage/blob/b4abe07f0fa9bac2cb70e4a3e315c2e7e5b08507/src/garage/torch/algos/pearl.py#L743-L746...
Hello, I am trying to run garage/examples/torch/maml_ppo_half_cheetah_dir.py and I would like to adapt the number of gradient steps that the algorithm takes for adaptation to a new task. Is there...
the new torch 1.5 works in different ways than 1.4 w.r.t to GPU usage. It will utilize the GPU, but will also try to maximize to maximize cpu ussage for...
As implemented in github.com/katerakelly/oyster, qf1 and qf2 should be differently initialized. Otherwise, two functions are always same because those are updated identically. Or, let me know what I am wrong....
https://github.com/rlworkgroup/garage/runs/2045693049?check_suite_focus=true#step:5:203
There is a potential bug in how alpha optimizer is initialized in MTSAC. During init we have: ``` self._log_alpha = torch.Tensor([self._initial_log_entropy] * self._num_tasks).requires_grad_() self._alpha_optimizer = optimizer([self._log_alpha] * self._num_tasks, lr=self._policy_lr) ```...
There appears to be a bug in wrap_experiment, where the function to create a file to store an archive of the launcher's git repo fails. Traceback: ``` tar (child): data/local/experiment/PONGNoFrameskip-v4_2/launch_archive.tar.xz:...
In this PR, I add a Pytorch version of the Categorical GRU Policy. I believe there is some in-progress work with adding RNN support #2172, however, this PR seems to...