paper-with-me

홈 › Papers

Modularity benefits reinforcement learning agents with competing homeostatic drives

2022-04-13 · Zack Dulberg, Rachit Dubey, Isabel M. Berwian, Jonathan D. Cohen

The problem of balancing conflicting needs is fundamental to intelligence. Standard reinforcement learning algorithms maximize a scalar reward, which requires combining different objective-specific rewards into a single number. Alternatively, different objectives could also be combined at the level of action value, such that specialist modules responsible for different objectives submit different action suggestions to a decision process, each based on rewards that are independent of one another. In this work, we explore the potential benefits of this alternative strategy. We investigate a biologically relevant multi-objective problem, the continual homeostasis of a set of variables, and compare a monolithic deep Q-network to a modular network with a dedicated Q-learner for each variable. We find that the modular agent: a) requires minimal exogenously determined exploration; b) has improved sample efficiency; and c) is more robust to out-of-domain perturbation.

📄 PDF Abstract BibTeX arXiv:2204.06608

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Homeostatic Coupling for Prosocial Behavior

2025-06-15 · Naoto Yoshida, Kingson Man

When regarding the suffering of others, we often experience personal distress and feel compelled to help\footnote{Preprint. Under review.}. Inspired by living systems, we investigate the emergence of prosocial behavior a…

Multi-agent Reinforcement Learning

Empathic Coupling of Homeostatic States for Intrinsic Prosociality

2024-11-16 · Naoto Yoshida, Kingson Man

When regarding the suffering of others, we often experience personal distress and feel compelled to help. Inspired by living systems, we investigate the emergence of prosocial behavior among autonomous agents that are mo…

Multi-agent Reinforcement Learning

Emotion-Inspired Learning Signals (EILS): A Homeostatic Framework for Adaptive Autonomous Agents

2025-12-20 · Dhruv Tiwari arxiv

The ruling method in modern Artificial Intelligence spanning from Deep Reinforcement Learning (DRL) to Large Language Models (LLMs) relies on a surge of static, externally defined reward functions. While this "extrinsic …

Reinforcement Learning

A Reinforcement Learning Theory for Homeostatic Regulation

2011-12-01 · NeurIPS 2011 12 · Mehdi Keramati, Boris S. Gutkin

Reinforcement learning models address animal's behavioral adaptation to its changing "external" environment, and are based on the assumption that Pavlovian, habitual and goal-directed responses seek to maximize reward ac…

Learning Theoryreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Cognitive Homeostatic Agents

2021-02-27 · Amol Kelkar

Human brain has been used as an inspiration for building autonomous agents, but it is not obvious what level of computational description of the brain one should use. This has led to overly opinionated symbolic approache…