期刊
NEURAL COMPUTATION
卷 33, 期 3, 页码 674-712出版社
MIT PRESS
DOI: 10.1162/neco_a_01357
关键词
-
资金
- Medical Research Council [MR/S502522/1]
- Wellcome Trust [088130/Z/09/Z]
- MRC [2088828] Funding Source: UKRI
Active inference is a first principle account of how autonomous agents operate in dynamic, nonstationary environments. In this paper, the authors provide an overview of active inference in a discrete state setting and compare it to reinforcement learning on the same environments. They show that active inference agents can perform epistemic exploration and account for uncertainty in a Bayesian optimal way, without the need for explicit rewards like in reinforcement learning. Additionally, the paper demonstrates how active inference agents can infer behaviors in reward-free environments compared to Q-learning and Bayesian model-based reinforcement learning agents.
Active inference is a first principle account of how autonomous agents operate in dynamic, nonstationary environments. This problem is also considered in reinforcement learning, but limited work exists on comparing the two approaches on the same discrete-state environments. In this letter, we provide (1) an accessible overview of the discrete-state formulation of active inference, highlighting natural behaviors in active inference that are generally engineered in reinforcement learning, and (2) an explicit discrete-state comparison between active inference and reinforcement learning on an OpenAI gym baseline. We begin by providing a condensed overview of the active inference literature, in particular viewing the various natural behaviors of active inference agents through the lens of reinforcement learning. We show that by operating in a pure belief-based setting, active inference agents can carry out epistemic exploration-and account for uncertainty about their environment-in a Bayes-optimal fashion. Furthermore, we show that the reliance on an explicit reward signal in reinforcement learning is removed in active inference, where reward can simply be treated as another observation we have a preference over; even in the total absence of rewards, agent behaviors are learned through preference learning. We make these properties explicit by showing two scenarios in which active inference agents can infer behaviors in reward-free environments compared to both Q-learning and Bayesian model-based reinforcement learning agents and by placing zero prior preferences over rewards and learning the prior preferences over the observations corresponding to reward. We conclude by noting that this formalism can be applied to more complex settings (e.g., robotic arm movement, Atari games) if appropriate generative models can be formulated. In short, we aim to demystify the behavior of active inference agents by presenting an accessible discrete state-space and time formulation and demonstrate these behaviors in a OpenAI gym environment, alongside reinforcement learning agents.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据