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

05/28/2021
by   Suyoung Lee, et al.
0

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.

READ FULL TEXT

page 15

page 17

research
07/06/2021

Meta-Reinforcement Learning for Heuristic Planning

In Meta-Reinforcement Learning (meta-RL) an agent is trained on a set of...
research
02/20/2023

Meta-World Conditional Neural Processes

We propose Meta-World Conditional Neural Processes (MW-CNP), a condition...
research
06/16/2020

Model-based Adversarial Meta-Reinforcement Learning

Meta-reinforcement learning (meta-RL) aims to learn from multiple traini...
research
10/26/2022

Uncertainty-based Meta-Reinforcement Learning for Robust Radar Tracking

Nowadays, Deep Learning (DL) methods often overcome the limitations of t...
research
11/02/2020

Information-theoretic Task Selection for Meta-Reinforcement Learning

In Meta-Reinforcement Learning (meta-RL) an agent is trained on a set of...
research
06/21/2022

Meta Reinforcement Learning with Finite Training Tasks – a Density Estimation Approach

In meta reinforcement learning (meta RL), an agent learns from a set of ...
research
11/17/2016

Learning to reinforcement learn

In recent years deep reinforcement learning (RL) systems have attained s...

Please sign up or login with your details

Forgot password? Click here to reset