search

rlworkgroup / garage

A toolkit for reproducible reinforcement learning research.
MIT License
1.84k stars 309 forks source link

Small bug in PEARLWorker #2246

Open eirik-thorp opened 3 years ago

eirik-thorp commented 3 years ago

Hi! I think there is a small bug in the PEARLWorker class for the PEARL algorithm. The ´deterministic´ variable should specify if the action should be sampled from the action distribution or if the action should be the mean of the distribution, but in the current implementation the action is always sampled even if ´deterministic == True´.

https://github.com/rlworkgroup/garage/blob/master/src/garage/torch/algos/pearl.py#L742-L745