Emergence of Structured Behaviors from Curiosity-Based Intrinsic Motivation

2018-02-21 · Nick Haber, Damian Mrowca, Li Fei-Fei, Daniel L. K. Yamins

Infants are experts at playing, with an amazing ability to generate novel structured behaviors in unstructured environments that lack clear extrinsic reward signals. We seek to replicate some of these abilities with a neural network that implements curiosity-driven intrinsic motivation. Using a simple but ecologically naturalistic simulated environment in which the agent can move and interact with objects it sees, the agent learns a world model predicting the dynamic consequences of its actions. Simultaneously, the agent learns to take actions that adversarially challenge the developing world model, pushing the agent to explore novel and informative interactions with its environment. We demonstrate that this policy leads to the self-supervised emergence of a spectrum of complex behaviors, including ego motion prediction, object attention, and object gathering. Moreover, the world model that the agent learns supports improved performance on object dynamics prediction and localization tasks. Our results are a proof-of-principle that computational models of intrinsic motivation might account for key features of developmental visuomotor learning in infants.

📄 PDF Abstract BibTeX arXiv:1802.07461

Code (0)

등록된 구현이 없습니다.

Tasks

motion predictionObject

Curiosity creates Diversity in Policy Search

2022-12-07 · Paul-Antoine Le Tolguenec, Emmanuel Rachelson, Yann Besse, Dennis G. Wilson

When searching for policies, reward-sparse environments often lack sufficient information about which behaviors to improve upon or avoid. In such environments, the policy search process is bound to blindly search for rew…

Diversity

Intrinsically motivated graph exploration using network theories of human curiosity

2023-07-11 · Shubhankar P. Patankar, Mathieu Ouellet, Juan Cervino, Alejandro Ribeiro 외

Intrinsically motivated exploration has proven useful for reinforcement learning, even without additional extrinsic rewards. When the environment is naturally represented as a graph, how to guide exploration best remains…

Graph Neural Network Recommendation Systems reinforcement-learning Reinforcement Learning

Curiosity-driven Exploration in Sparse-reward Multi-agent Reinforcement Learning

2023-02-21 · Jiong Li, Pratik Gajane

Sparsity of rewards while applying a deep reinforcement learning method negatively affects its sample-efficiency. A viable solution to deal with the sparsity of rewards is to learn via intrinsic motivation which advocate…

Deep Reinforcement Learning Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning+1

Multi-Agent Empowerment and Emergence of Complex Behavior in Groups

2026-04-22 · Tristan Shah, Ilya Nemenman, Daniel Polani, Stas Tiomkin arxiv

Intrinsic motivations are receiving increasing attention, i.e. behavioral incentives that are not engineered, but emerge from the interaction of an agent with its surroundings. In this work we study the emergence of beha…

Learning to Play With Intrinsically-Motivated, Self-Aware Agents

2018-12-01 · NeurIPS 2018 12 · Nick Haber, Damian Mrowca, Stephanie Wang, Li F. Fei-Fei 외

motion prediction Object