Repository Issue Activity (beta)

#458 Upgrade plans to later Python & Gymnasium

#429 Link broken in file rl_intro3.rst

#456 Add recommended system requirements for running in a Ubuntu VM

#455 Documentation update

#454 Simplest policy gradient code implementation assumes uniform episode lengths?

#400 Working installable version of SpinningUp for PyTorch and MacOS

#137 Early Stopping When Approximate KL Divergence is Negative in PPO

#359 I can not install box2d-py

#415 Cannot install python 3.6 in mac using conda

#436 Why is there a minus sign in the loss function of simplest policy gradient in part 3?

#446 Links broken to content.

#447 Is This the Best RL Implementation for Robotics Simulation (e.g., PPO)?

#396 ERROR: Failed building wheel opencv-python

#444 Spinning Up not working on M1 MacBooks – Working fork with fixes

#424 `BUG` VPG: `pi_info_old` seems to be the same as `pi_info`

#443 TRPO KL Divergence Direction

#440 Failed to integrate with CUDA GPU

#3 Docker support would be great

#32 Failed building wheel for box2d-py [solved]

#414 The compute_loss function is wrong for the Simplest Policy Gradient

#377 Running spinningup in WSL2 with WSLg on Windows (Success)

#435 issue: watch a video of the trained policy

#437 Working simplified version of Spinning Up that works on Windows + Pytorch (CPU)

#427 ModuleNotFoundError: No module named 'spinup.algos'

#433 Rewards-to-Go issue