Reinforcement Learning For Robotics And Control With Active Uncertainty Reduction

Abstract

Model-free reinforcement learning based methods such as Proximal Policy Optimization, or Q-learning typically require thousands of interactions with the environment to approximate the optimum controller which may not always be feasible in robotics due to safety and time consumption. Model-based methods such as PILCO or BlackDrops, while data-efficient, provide solutions with limited robustness and complexity. To address this tradeoff, we introduce active uncertainty reduction-based virtual environments, which are formed through limited trials conducted in the original environment. We provide an efficient method for uncertainty management, which is used as a metric for self-improvement by identification of the points with maximum expected improvement through adaptive sampling. Capturing the uncertainty also allows for better mimicking of the reward responses of the original system. Our approach enables the use of complex policy structures and reward functions through a unique combinatio

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keypatwardhan2019reinforcement

Related papers

• How To Enable Uncertainty Estimation In Proximal Policy Optimization (2022)0.00
• Deep Model-based Reinforcement Learning Via Estimated Uncertainty And Conservative Policy Optimization (2019)0.00
• Online Robust Reinforcement Learning With Model Uncertainty (2021)0.00
• Actively Learning Reinforcement Learning: A Stochastic Optimal Control Approach (2023)0.00
• Efficient Model-based Reinforcement Learning Through Optimistic Policy Search And Planning (2020)0.00
• Uncertainty-aware Policy Optimization: A Robust, Adaptive Trust Region Approach (2020)0.00
• Safety Correction From Baseline: Towards The Risk-aware Policy In Robotics Via Dual-agent Reinforcement Learning (2022)3.58
• Towards Model-based Reinforcement Learning For Industry-near Environments (2019)5.84