Model-Free Episodic Control
This addresses the problem of slow learning in AI for sequential decision-making, offering a biologically-inspired incremental improvement.
The paper tackles the slow learning of deep reinforcement learning algorithms by proposing a model of hippocampal episodic control, which learns significantly faster and achieves higher overall reward on challenging tasks.
State of the art deep reinforcement learning algorithms take many millions of interactions to attain human-level performance. Humans, on the other hand, can very quickly exploit highly rewarding nuances of an environment upon first discovery. In the brain, such rapid learning is thought to depend on the hippocampus and its capacity for episodic memory. Here we investigate whether a simple model of hippocampal episodic control can learn to solve difficult sequential decision-making tasks. We demonstrate that it not only attains a highly rewarding strategy significantly faster than state-of-the-art deep reinforcement learning algorithms, but also achieves a higher overall reward on some of the more challenging domains.