mirror of
https://github.com/gryf/coach.git
synced 2025-12-17 11:10:20 +01:00
Dueling DDQN
Each experiment uses 3 seeds and is trained for 10k environment steps. The parameters used for Dueling DDQN are the same parameters as described in the original paper.
Pong Dueling DDQN - single worker
coach -p Atari_Dueling_DDQN -lvl pong
Breakout Dueling DDQN - single worker
coach -p Atari_Dueling_DDQN -lvl breakout
Space Invaders Dueling DDQN - single worker
coach -p Atari_Dueling_DDQN -lvl space_invaders