Safety Augmented Value Estimation from Demonstrations (SAVED): Safe Deep Model-Based RL for Sparse Cost Robotic Tasks

Abstract

Reinforcement learning (RL) for robotics is challenging due to the difficulty in hand-engineering a dense cost function, which can lead to unintended behavior, and dynamical uncertainty, which makes exploration and constraint satisfaction challenging. We address these issues with a new model-based reinforcement learning algorithm, Safety Augmented Value Estimation from Demonstrations (SAVED), which uses supervision that only identifies task completion and a modest set of suboptimal demonstrations to constrain exploration and learn efficiently while handling complex constraints. We then compare SAVED with 3 state-of-the-art model-based and model-free RL algorithms on 6 standard simulation benchmarks involving navigation and manipulation and a physical knot-tying task on the da Vinci surgical robot. Results suggest that SAVED outperforms prior methods in terms of success rate, constraint satisfaction, and sample efficiency, making it feasible to safely learn a control policy directly on a real robot in less than an hour. For tasks on the robot, baselines succeed less than 5% of the time while SAVED has a success rate of over 75% in the first 50 training iterations. Code and supplementary material is available at https://tinyurl.com/saved-rl.

Robotics and Automation Letters and International Conference on Robotics and Automation 2020. First two authors contributed equally

References in corpus (13)

• Continuous control with deep reinforcement learning
• Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
• Trust Region Policy Optimization
• Addressing Function Approximation Error in Actor-Critic Methods
• Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards
• Hindsight Experience Replay
• #Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning
• Safe Model-based Reinforcement Learning with Stability Guarantees
• Deep Q-learning from Demonstrations
• Unifying Count-Based Exploration and Intrinsic Motivation
• Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research
• EX2: Exploration with Exemplar Models for Deep Reinforcement Learning
• On-Policy Robot Imitation Learning from a Converging Supervisor

Cited by in corpus (5)

• A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithms
• Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences
• On-Policy Robot Imitation Learning from a Converging Supervisor
• Deep Bayesian Reward Learning from Preferences
• Safe Interactive Model-Based Learning