SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference
This work addresses the high computational cost and inefficiency in reinforcement learning experiments, offering a practical solution for researchers and practitioners.
The paper tackles the problem of scaling deep reinforcement learning by introducing SEED RL, a scalable and efficient agent that trains on millions of frames per second and reduces experiment costs by 40% to 80% compared to current methods.
We present a modern scalable reinforcement learning agent called SEED (Scalable, Efficient Deep-RL). By effectively utilizing 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 three times 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.