Discriminator Augmented Model-Based Reinforcement Learning

Abstract

By planning through a learned dynamics model, model-based reinforcement learning (MBRL) offers the prospect of good performance with little environment interaction. However, it is common in practice for the learned model to be inaccurate, impairing planning and leading to poor performance. This paper aims to improve planning with an importance sampling framework that accounts and corrects for discrepancy between the true and learned dynamics. This framework also motivates an alternative objective for fitting the dynamics model: to minimize the variance of value estimation during planning. We derive and implement this objective, which encourages better prediction on trajectories with larger returns. We observe empirically that our approach improves the performance of current MBRL algorithms on two stochastic control problems, and provide a theoretical basis for our method.

References in corpus (13)

• Continuous control with deep reinforcement learning
• Gaussian Processes for Data-Efficient Learning in Robotics and Control
• Model-Based Reinforcement Learning for Atari
• Learning Latent Dynamics for Planning from Pixels
• Benchmarking Model-Based Reinforcement Learning
• Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning
• Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion
• Exploring Model-based Planning with Policy Networks
• Dynamics-Aware Unsupervised Discovery of Skills
• Model Predictive Path Integral Control using Covariance Variable Importance Sampling
• Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control
• Goal-Aware Prediction: Learning to Model What Matters
• Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers