cogment / cogment-verse

Research platform for Human-in-the-loop learning (HILL) & Multi-Agent Reinforcement Learning (MARL)
https://cogment.ai/cogment_verse
Apache License 2.0
80 stars 15 forks source link

Dev ppo #91

Closed lhnguyen102 closed 2 years ago

lhnguyen102 commented 2 years ago

Features

Run command for mujoco python -m main +experiment=ppo/hopper

saikrishna-1996 commented 2 years ago

Do we need the file profile_stats_0.stats ?

lhnguyen102 commented 2 years ago

@saikrishna-1996 You're right. We don't need this file profile_stats_0.stats. I will remove it. Thank you!

vabdollahi commented 2 years ago

Being a non-expert in PPO, the implementation seems neat to me.

lhnguyen102 commented 2 years ago

@saikrishna-1996 @vabdollahi, if you don't have any other comments, please approve my PR. Thanks!