search

rail-berkeley / rlkit

Collection of reinforcement learning algorithms
MIT License
2.5k stars 553 forks source link

removed extraneous full_observation appendage #29

Closed richardrl closed 5 years ago

richardrl commented 5 years ago

I believe full_observations, observations, reward, terminals should have the same length

This extra append makes full_observation +1 over the other lists of the path