Skip to content
This repository was archived by the owner on Dec 11, 2022. It is now read-only.

Files

Latest commit

 

History

History

dueling_ddqn_with_per

Dueling DDQN with Prioritized Experience Replay

Each experiment uses 3 seeds and is trained for 10k environment steps. The parameters used for Dueling DDQN with PER are the same parameters as described in the following paper.

Breakout Dueling DDQN with PER - single worker

coach -p Atari_Dueling_DDQN_with_PER_OpenAI -lvl breakout

Breakout Dueling DDQN with PER

Pong Dueling DDQN with PER - single worker

coach -p Atari_Dueling_DDQN_with_PER_OpenAI -lvl pong

Pong Dueling DDQN with PER

Space Invaders Dueling DDQN with PER - single worker

coach -p Atari_Dueling_DDQN_with_PER_OpenAI -lvl space_invaders

Space Invaders Dueling DDQN with PER