bentrevett/pytorch-rl

Tutorials for reinforcement learning in PyTorch and Gym by implementing a few of the popular algorithms. [IN PROGRESS]

Jupyter NotebookMIT

Issues

Adding a sample_action method for ActorCritic
#4 opened 3 years ago by lemikhovalex
0
3 - Advantage Actor Critic (A2C) [CartPole].ipynb - Returns do not need to be detached
#3 opened 3 years ago by nimrare
0
actor critic possible error
#2 opened 4 years ago by hawkeoni
2
Taking 'done' into consideration while calculating returns
#1 opened 4 years ago by murtazabasu
1