lcswillems/torch-ac
Recurrent and multi-process PyTorch implementation of deep reinforcement Actor-Critic algorithms A2C and PPO
PythonMIT
Issues
- 3
- 3
Small bug in algos/base.py
#11 opened by anniezhi - 0
- 1
multiprocessing (fork issue)
#7 opened by delamarifer - 2
- 1
Support for Multi-agent?
#1 opened by chen-zichen