Alert button
Picture for Vedavyas Panneershelvam

Vedavyas Panneershelvam

Alert button

Massively Parallel Methods for Deep Reinforcement Learning

Jul 16, 2015
Arun Nair, Praveen Srinivasan, Sam Blackwell, Cagdas Alcicek, Rory Fearon, Alessandro De Maria, Vedavyas Panneershelvam, Mustafa Suleyman, Charles Beattie, Stig Petersen, Shane Legg, Volodymyr Mnih, Koray Kavukcuoglu, David Silver

Figure 1 for Massively Parallel Methods for Deep Reinforcement Learning
Figure 2 for Massively Parallel Methods for Deep Reinforcement Learning
Figure 3 for Massively Parallel Methods for Deep Reinforcement Learning
Figure 4 for Massively Parallel Methods for Deep Reinforcement Learning

We present the first massively distributed architecture for deep reinforcement learning. This architecture uses four main components: parallel actors that generate new behaviour; parallel learners that are trained from stored experience; a distributed neural network to represent the value function or behaviour policy; and a distributed store of experience. We used our architecture to implement the Deep Q-Network algorithm (DQN). Our distributed algorithm was applied to 49 games from Atari 2600 games from the Arcade Learning Environment, using identical hyperparameters. Our performance surpassed non-distributed DQN in 41 of the 49 games and also reduced the wall-time required to achieve these results by an order of magnitude on most games.

* Presented at the Deep Learning Workshop, International Conference on Machine Learning, Lille, France, 2015 
Viaarxiv icon