Fast deep reinforcement learning using online adjustments from the past

Code

• github.com/deepmind/open_spiel
  none★ 5,095
• github.com/AnnaNikitaRL/EVA
  pytorch★ 4

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 planning 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 EVAis performant on a demonstration task and Atari games.

Tasks

Reproductions