pytorch_ppo_rl
pytorch_ppo_rl copied to clipboard
Pytorch implementation of intrinsic curiosity module with proximal policy optimization
Results
2
pytorch_ppo_rl issues
Sort by
recently updated
recently updated
newest added
Hi, I also tried to reproduce your results for "MountainCar-v0" but training had no any progress after more than 5k episodes(more than 4 hours).
Hi, I tried to reproduce your results for LunarLander but training had not converged after more than 5k episodes with either 4 or 8 workers. Can you share the number...