cosmicBboy / ml-research

Research projects in Machine Learning
MIT License
6 stars 2 forks source link

[metalearn] support PPO training algorithm #25

Open cosmicBboy opened 4 years ago

cosmicBboy commented 4 years ago

To improve stability and robustness of policy, implement proximal policy optimization (PPO):

cosmicBboy commented 4 years ago

https://github.com/ikostrikov/pytorch-a2c-ppo-acktr-gail/blob/master/a2c_ppo_acktr/algo/ppo.py#L61-L66