keiohta / tf2rl

TensorFlow2 Reinforcement Learning
MIT License
461 stars 104 forks source link

Example of GAIFO for atari? #161

Open rrags opened 2 years ago

rrags commented 2 years ago

I tried to make my own using atari categorical actor critic for PPO, but I always get this error: ` /home/rj/.local/lib/python3.8/site-packages/tf2rl/algos/vpg.py:187 _get_action_body * action, logp = self.actor_critic(state, test)

ValueError: too many values to unpack (expected 2)

`