In this paper, we begin with an agent using an artificial neural network to improve its behavior in an environment with extreme perceptual aliasing. We then improve the performance of using an episodic memory. In particular, a memory of past events allows the agent to distinguish it’s present state from other states that are perceived identically. We describe steps we took to leverage this memory and remove the manual tuning required for the agent to perform in each specific environment.

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

Using Episodic Memory to Aid Machine Learning Performance in Perceptually Aliased Environments

  • Jayven Caesar Cachola,
  • Penny Silliman,
  • Andrew Nuxoll

摘要

In this paper, we begin with an agent using an artificial neural network to improve its behavior in an environment with extreme perceptual aliasing. We then improve the performance of using an episodic memory. In particular, a memory of past events allows the agent to distinguish it’s present state from other states that are perceived identically. We describe steps we took to leverage this memory and remove the manual tuning required for the agent to perform in each specific environment.