Joy, distress, hope, and fear in reinforcement learning
نویسندگان
چکیده
In this paper we present a mapping between joy, distress, hope and fear, and Reinforcement Learning primitives. Joy / distress is a signal that is derived from the RL update signal, while hope/fear is derived from the utility of the current state. Agent-based simulation experiments replicate psychological and behavioral dynamics of emotion including: joy and distress reactions that develop prior to hope and fear; fear extinction; habituation of joy; and, task randomness that increases the intensity of joy and distress. This work distinguishes itself by assessing the dynamics of emotion in an adaptive agent framework coupling it to the literature on habituation, development, and extinction.
منابع مشابه
Emergent Dynamics of Joy, Distress, Hope and Fear in Reinforcement Learning Agents
We report on a study that shows plausible emotion dynamics for joy, distress, hope and fear, emerging in an adaptive agent that uses Reinforcement Learning (RL) to adapt to a task. Joy/distress is a signal that is derived from the RL update signal, while hope/fear is derived from the utility of the current state. Agent-based simulation experiments replicate psychological and behavioral dynamics...
متن کاملA reinforcement learning model of joy, distress, hope and fear
In this paper we computationally study the relation between adaptive behavior and emotion. Using the Reinforcement Learning framework, we propose that learned state utility, V(s), models fear (negative) and hope (positive) based on the fact that both signals are about anticipation of loss or gain. Further, we propose that joy/distress is a signal similar to the error signal. We present agent-ba...
متن کاملFear and Hope Emerge from Anticipation in Model-Based Reinforcement Learning
Social agents and robots will require both learning and emotional capabilities to successfully enter society. This paper connects both challenges, by studying models of emotion generation in sequential decision-making agents. Previous work in this field has focussed on model-free reinforcement learning (RL). However, important emotions like hope and fear need anticipation, which requires a mode...
متن کاملCombating Reinforcement Learning's Sisyphean Curse with Intrinsic Fear
To use deep reinforcement learning in the wild, we might hope for an agent that would never make catastrophic mistakes. At the very least, we could hope that an agent would eventually learn to avoid old mistakes. Unfortunately, even in simple environments, modern deep reinforcement learning techniques are doomed by a Sisyphean curse. Owing to the use of function approximation, these agents even...
متن کاملFacial Expression Learning 3 Au 1 DANIEL
17 Theoretical Background 18 Facial expression learning is typically a focus of theories of 19 emotional development. These theories differ in the 20 importance they assign to innate versus environmental 21 factors, and the degree to which they emphasize change 22 in the form of facial expressions with age. Learning theory 23 argues that the development of facial expression proceeds 24 through ...
متن کامل