Closed hanbaoan123 closed 3 years ago
Another parameter (weight w) should be input into the train funtion when using dqn with prioritized_replay.
The implementation of PrioritizedReplayBuffer stores prioritized weights in variable transitions. See a comparison between PrioritizedReplayBuffer.sample and ReplayBuffer.sample.
PrioritizedReplayBuffer
transitions
Another parameter (weight w) should be input into the train funtion when using dqn with prioritized_replay.