paper-with-me

Papers

Exploring Exploration: Comparing Children with RL Agents in Unified Environments

2020-05-06 · Eliza Kosoy, Jasmine Collins, David M. Chan, Sandy Huang, Deepak Pathak, Pulkit Agrawal, John Canny, Alison Gopnik, Jessica B. Hamrick

Research in developmental psychology consistently shows that children explore the world thoroughly and efficiently and that this exploration allows them to learn. In turn, this early learning supports more robust generalization and intelligent behavior later in life. While much work has gone into developing methods for exploration in machine learning, artificial agents have not yet reached the high standard set by their human counterparts. In this work we propose using DeepMind Lab (Beattie et al., 2016) as a platform to directly compare child and agent behaviors and to develop new exploration techniques. We outline two ongoing experiments to demonstrate the effectiveness of a direct comparison, and outline a number of open research questions that we believe can be tested using this methodology.

📄 PDF Abstract BibTeX arXiv:2005.02880

Code (1)

CannyLab/ExpExp 공식 구현

Similar Papers 제목 키워드 기반

Learning Causal Overhypotheses through Exploration in Children and Computational Models

2022-02-21 · Eliza Kosoy, Adrian Liu, Jasmine Collins, David M Chan 외

Despite recent progress in reinforcement learning (RL), RL algorithms for exploration still remain an active area of research. Existing methods often focus on state-based metrics, which do not consider the underlying cau…

Causal InferenceEfficient ExplorationReinforcement Learning (RL)

Intrinsically-Motivated Humans and Agents in Open-World Exploration

2025-03-31 · Aly Lidayan, Yuqing Du, Eliza Kosoy, Maria Rufova 외

What drives exploration? Understanding intrinsic motivation is a long-standing challenge in both cognitive science and artificial intelligence; numerous objectives have been proposed and used to train agents, yet there r…

Diversity

Language-Goal Imagination to Foster Creative Exploration in Deep RL

2020-06-12 · ICML Workshop LaReL 2020 7 · Tristan Karch, Nicolas Lair, Cédric Colas, Jean-Michel Dussoux 외

Developmental machine learning studies how artificial agents can model the way children learn open-ended repertoires of skills. Children are known to use language and its compositionality as a tool to imagine description…

Language Grounding through Social Interactions and Curiosity-Driven Multi-Goal Learning

2019-11-08 · Nicolas Lair, Cédric Colas, Rémy Portelas, Jean-Michel Dussoux 외

Autonomous reinforcement learning agents, like children, do not have access to predefined goals and reward functions. They must discover potential goals, learn their own reward functions and engage in their own learning …

Active LearningDescriptiveReinforcement Learning

Language as a Cognitive Tool to Imagine Goals in Curiosity-Driven Exploration

2020-02-21 · Cédric Colas, Tristan Karch, Nicolas Lair, Jean-Michel Dussoux 외

Developmental machine learning studies how artificial agents can model the way children learn open-ended repertoires of skills. Such agents need to create and represent goals, select which ones to pursue and learn to ach…

Deep Reinforcement LearningLanguage AcquisitionLanguage ModellingReinforcement Learning