Exploring Exploration: Comparing Children with RL Agents in Unified Environments
arXiv:2005.02880
Abstract
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.
Published as a workshop paper at "Bridging AI and Cognitive Science" (ICLR 2020)
References in corpus (9)
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Active Learning of Inverse Models with Intrinsically Motivated Goal Exploration in Robots
- #Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning
- Exploration by Random Network Distillation
- Investigating Human Priors for Playing Video Games
- EX2: Exploration with Exemplar Models for Deep Reinforcement Learning
- Environmental drivers of systematicity and generalization in a situated agent
- Self-Supervised Exploration via Disagreement
- ZPD Teaching Strategies for Deep Reinforcement Learning from Demonstrations