Model-based Active Exploration

Abstract

Efficient exploration is an unsolved problem in Reinforcement Learning which is usually addressed by reactively rewarding the agent for fortuitously encountering novel situations. This paper introduces an efficient active exploration algorithm, Model-Based Active eXploration (MAX), which uses an ensemble of forward models to plan to observe novel events. This is carried out by optimizing agent behaviour with respect to a measure of novelty derived from the Bayesian perspective of exploration, which is estimated using the disagreement between the futures predicted by the ensemble members. We show empirically that in semi-random discrete environments where directed exploration is critical to make progress, MAX is at least an order of magnitude more efficient than strong baselines. MAX scales to high-dimensional continuous environments where it builds task-agnostic models that can be used for any downstream task.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyshyam2018model

Related papers

• Sample Efficient Reinforcement Learning Via Model-ensemble Exploration And Exploitation (2021)0.00
• Off-policy Reinforcement Learning With Model-based Exploration Augmentation (2025)0.00
• Ensemble Value Functions For Efficient Exploration In Multi-agent Reinforcement Learning (2023)0.00
• Dynamic Subgoal-based Exploration Via Bayesian Optimization (2019)0.00
• Learning Off-policy With Model-based Intrinsic Motivation For Active Online Exploration (2024)0.00
• Active Exploration In Markov Decision Processes (2019)0.00
• Modeling Human Exploration Through Resource-rational Reinforcement Learning (2022)2.26
• Fast Active Learning For Pure Exploration In Reinforcement Learning (2020)0.00