COBRA: Data-efficient Model-based RL Through Unsupervised Object Discovery And Curiosity-driven Exploration

Abstract

Data efficiency and robustness to task-irrelevant perturbations are long-standing challenges for deep reinforcement learning algorithms. Here we introduce a modular approach to addressing these challenges in a continuous control environment, without using hand-crafted or supervised information. Our Curious Object-Based seaRch Agent (COBRA) uses task-free intrinsically motivated exploration and unsupervised learning to build object-based models of its environment and action space. Subsequently, it can learn a variety of tasks through model-based search in very few steps and excel on structured hold-out tests of policy robustness.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywatters2019cobra

Related papers

• Learning Off-policy With Model-based Intrinsic Motivation For Active Online Exploration (2024)0.00
• CUDC: A Curiosity-driven Unsupervised Data Collection Method With Adaptive Temporal Distances For Offline Reinforcement Learning (2023)2.26
• AXIOM: Learning To Play Games In Minutes With Expanding Object-centric Models (2025)0.00
• Fast Exploration With Simplified Models And Approximately Optimistic Planning In Model Based Reinforcement Learning (2018)0.00
• Wonder Wins Ways: Curiosity-driven Exploration Through Multi-agent Contextual Calibration (2025)0.00
• Curiosity-driven Exploration Via Latent Bayesian Surprise (2021)0.00
• Multi-objective Model-based Policy Search For Data-efficient Learning With Sparse Rewards (2018)0.00
• Curiosity-driven Multi-agent Exploration With Mixed Objectives (2022)0.00