coach/benchmarks/qr_dqn

Quantile Regression DQN

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.

Breakout QR-DQN - single worker

python3 coach.py -p Atari_QR_DQN -lvl breakout

Pong QR-DQN - single worker

python3 coach.py -p Atari_QR_DQN -lvl pong