Fast Deep Reinforcement Learning Using Online Adjustments From The Past

Authors:
Steven Hansen DeepMind
Alexander Pritzel Deepmind
Pablo Sprechmann DeepMind
Andre Barreto DeepMind
Charles Blundell DeepMind

Introduction:

The authors propose Ephemeral Value Adjusments (EVA): a means of allowing deep reinforcement learning agents to rapidly adapt to experience in their replay buffer.EVA shifts the value predicted by a neural network with an estimate of the value function found by prioritised sweeping over experience tuples from the replay buffer near the current state.

Abstract:

We propose Ephemeral Value Adjusments (EVA): a means of allowing deep reinforcement learning agents to rapidly adapt to experience in their replay buffer.EVA shifts the value predicted by a neural network with an estimate of the value function found by prioritised sweeping over experience tuples from the replay buffer near the current state. EVA combines a number of recent ideas around combining episodic memory-like structures into reinforcement learning agents: slot-based storage, content-based retrieval, and memory-based planning.We show that EVA is performant on a demonstration task and Atari games.

You may want to know: