Learning Causal Overhypotheses Through Exploration In Children And Computational Models

Abstract

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 causal structures of the environment, and while recent research has begun to explore RL environments for causal learning, these environments primarily leverage causal information through causal inference or induction rather than exploration. In contrast, human children - some of the most proficient explorers - have been shown to use causal information to great benefit. In this work, we introduce a novel RL environment designed with a controllable causal structure, which allows us to evaluate exploration strategies used by both agents and children in a unified environment. In addition, through experimentation on both computation models and children, we demonstrate that there are significant differences between information-gain optimal RL exploration in causal environments a

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keykosoy2022learning

Related papers

• Learning By Doing: An Online Causal Reinforcement Learning Framework With Causal-aware Policy (2024)1.56
• Boosting Efficiency In Task-agnostic Exploration Through Causal Knowledge (2024)0.00
• Causal Reinforcement Learning Using Observational And Interventional Data (2021)0.00
• Disentangling Causal Effects For Hierarchical Reinforcement Learning (2020)0.00
• Learning Nonlinear Causal Reductions To Explain Reinforcement Learning Policies (2025)0.00
• Explainable Reinforcement Learning Via A Causal World Model (2023)9.03
• Why Online Reinforcement Learning Is Causal (2024)0.00
• Explainable Reinforcement Learning Through A Causal Lens (2019)16.69