a bug in tutorial_prioritized_replay.py?

tensorlayer / TensorLayer

Deep Learning and Reinforcement Learning Library for Scientists and Engineers

http://tensorlayerx.com

Other

7.33k stars 1.61k forks source link

Closed hanbaoan123 closed 3 years ago

hanbaoan123 commented 4 years ago

Another parameter (weight w) should be input into the train funtion when using dqn with prioritized_replay.

Officium commented 3 years ago

The implementation of PrioritizedReplayBuffer stores prioritized weights in variable transitions. See a comparison between PrioritizedReplayBuffer.sample and ReplayBuffer.sample.