Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning

by   Younggyo Seo, et al.

Model-based reinforcement learning (RL) has shown great potential in various control tasks in terms of both sample-efficiency and final performance. However, learning a generalizable dynamics model robust to changes in dynamics remains a challenge since the target transition dynamics follow a multi-modal distribution. In this paper, we present a new model-based RL algorithm, coined trajectory-wise multiple choice learning, that learns a multi-headed dynamics model for dynamics generalization. The main idea is updating the most accurate prediction head to specialize each head in certain environments with similar dynamics, i.e., clustering environments. Moreover, we incorporate context learning, which encodes dynamics-specific information from past experiences into the context latent vector, enabling the model to perform online adaptation to unseen environments. Finally, to utilize the specialized prediction heads more effectively, we propose an adaptive planning method, which selects the most accurate prediction head over a recent experience. Our method exhibits superior zero-shot generalization performance across a variety of control tasks, compared to state-of-the-art RL methods. Source code and videos are available at


A Relational Intervention Approach for Unsupervised Dynamics Generalization in Model-Based Reinforcement Learning

The generalization of model-based reinforcement learning (MBRL) methods ...

Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning

Model-based reinforcement learning (RL) enjoys several benefits, such as...

Task-Agnostic Dynamics Priors for Deep Reinforcement Learning

While model-based deep reinforcement learning (RL) holds great promise f...

Decomposed Mutual Information Optimization for Generalized Context in Meta-Reinforcement Learning

Adapting to the changes in transition dynamics is essential in robotic a...

Prototypical context-aware dynamics generalization for high-dimensional model-based reinforcement learning

The latent world model provides a promising way to learn policies in a c...

Few Shot System Identification for Reinforcement Learning

Learning by interaction is the key to skill acquisition for most living ...

Please sign up or login with your details

Forgot password? Click here to reset