Ape-X DPG

Introduced by Horgan et al. in Distributed Prioritized Experience Replay

Ape-X DPG combines DDPG with distributed prioritized experience replay through the Ape-X architecture.

Source: Distributed Prioritized Experience Replay

Paper	Code	Results	Date	Stars

Task	Papers	Share
Atari Games	1	50.00%
Reinforcement Learning (RL)	1	50.00%

This feature is experimental; we are continuously improving our matching algorithm.

Component	Type	Add Remove
Ape-X	Distributed Reinforcement Learning
DDPG	Policy Gradient Methods