offline-rl.github.io - An Optimistic Perspective on Offline Reinforcement Learning

home > domains > offline-rl.github.io

Example domain paragraphs

The DQN Replay Dataset was collected as follows: We first train a DQN agent, on all 60 Atari 2600 games with sticky actions enabled for 200 million frames (standard protocol) and save all of the experience tuples of (observation, action, reward, next observation) (approximately 50 million) encountered during training. We repeat this process five times for each game.

This logged DQN data can be found in the public GCP bucket gs://atari-replay-datasets which can be downloaded using gsutil . To install gsutil, follow the instructions here .

After installing gsutil, run the command to copy the entire dataset:

Links to offline-rl.github.io (2)

• norouzi.github.io Mohammad Norouzi
• agarwl.github.io Rishabh Agarwal – Google Brain