Learning to Reweight Imaginary Transitions for Model-Based Reinforcement Learning

Abstract

Model-based reinforcement learning (RL) is more sample efficient than model-free RL by using imaginary trajectories generated by the learned dynamics model. When the model is inaccurate or biased, imaginary trajectories may be deleterious for training the action-value and policy functions. To alleviate such problem, this paper proposes to adaptively reweight the imaginary transitions, so as to reduce the negative effects of poorly generated trajectories. More specifically, we evaluate the effect of an imaginary transition by calculating the change of the loss computed on the real samples when we use the transition to train the action-value and policy functions. Based on this evaluation criterion, we construct the idea of reweighting each imaginary transition by a well-designed meta-gradient algorithm. Extensive experimental results demonstrate that our method outperforms state-of-the-art model-based and model-free RL algorithms on multiple tasks. Visualization of our changing weights further validates the necessity of utilizing reweight scheme.

References in corpus (13)

• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Addressing Function Approximation Error in Actor-Critic Methods
• Soft Actor-Critic Algorithms and Applications
• Learning Continuous Control Policies by Stochastic Value Gradients
• Model-Ensemble Trust-Region Policy Optimization
• Benchmarking Model-Based Reinforcement Learning
• Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
• Meta-Gradient Reinforcement Learning
• Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees
• Model-Based Reinforcement Learning via Meta-Policy Optimization
• Exploring Model-based Planning with Policy Networks
• Discovery of Useful Questions as Auxiliary Tasks
• On Learning Intrinsic Rewards for Policy Gradient Methods