“SEED RL: Scalable and Efficient Deep-RL With Accelerated Central Inference”, 2019-10-15 (; similar):
We present a modern scalable reinforcement learning agent called SEED (Scalable, Efficient Deep-RL). By effectively using modern accelerators, we show that it is not only possible to train on millions of frames per second but also to lower the cost of experiments compared to current methods. We achieve this with a simple architecture that features centralized inference and an optimized communication layer.
SEED adopts two state-of-the-art distributed algorithms, IMPALA/V-trace (policy gradients) and R2D2 (Q-learning), and is evaluated on Atari-57, DeepMind Lab and Google Research Football. We improve the state-of-the-art on Football and are able to reach state-of-the-art on Atari-57 3× faster in wall-time.
For the scenarios we consider, a 40% to 80% cost reduction for running experiments is achieved.
The implementation along with experiments is open-sourced so results can be reproduced and novel ideas tried out.