MarcoMeter/recurrent-ppo-truncated-bptt

Baseline implementation of recurrent PPO using truncated BPTT

语言：Jupyter Notebook · GitHub 星标：160 · Fork：20

话题：actor-critic · bptt · deep-learning · deep-reinforcement-learning · gru · lstm · on-policy · policy-gradient

在 GitHub 上查看原仓库