Agent not learning for maze environment with CRAR

VinF / deer

DEEp Reinforcement learning framework

Other

485 stars 126 forks source link

Agent not learning for maze environment with CRAR #78

Closed parthchadha closed 4 years ago

parthchadha commented 4 years ago

I am trying to reproduce the results of the CRAR agent in the maze environment and am observing that the agent's test reward is not improving at all. It stays at about -5 for all the 250 epochs. Can you please point me to the experiment settings that can reproduce the results?

VinF commented 4 years ago

Hi Parth,

Thanks for reaching out. The value for the learning rate of the representation loss in CRAR is set to a different value for that experiment: https://github.com/VinF/deer/blob/83bf5338d92393a35b79b8bfe2d1c25f30cd52f8/deer/learning_algos/CRAR_keras.py#L583 It must be set at the value self._lr instead of self._lr/5. Please let me know if you still run into problems.

Apologies for this hard coded value.

parthchadha commented 4 years ago

Hi Vincent, Thanks for pointing this out. I am able to reproduce the results now!