Each experiment uses 3 seeds and is trained for 10k environment steps. The parameters used for QR-DQN are the same parameters as described in the original paper.
coach -p Atari_QR_DQN -lvl breakout
coach -p Atari_QR_DQN -lvl pong
qr_dqn
Folders and files
| Name | Name | Last commit date | ||
|---|---|---|---|---|
parent directory.. | ||||