Improving Generalization in Meta-RL with Imaginary Tasks from Latent Dynamics Mixture

Part of Advances in Neural Information Processing Systems 34 pre-proceedings (NeurIPS 2021)

Paper Supplemental

Bibtek download is not available in the pre-proceeding


Authors

Suyoung Lee, Sae-Young Chung

Abstract

The generalization ability of most meta-reinforcement learning (meta-RL) methods is largely limited to test tasks that are sampled from the same distribution used to sample training tasks. To overcome the limitation, we propose Latent Dynamics Mixture (LDM) that trains a reinforcement learning agent with imaginary tasks generated from mixtures of learned latent dynamics. By training a policy on mixture tasks along with original training tasks, LDM allows the agent to prepare for unseen test tasks during training and prevents the agent from overfitting the training tasks. LDM significantly outperforms standard meta-RL methods in test returns on the gridworld navigation and MuJoCo tasks where we strictly separate the training task distribution and the test task distribution.