Meta-Reinforcement Learning in Broad and Non-Parametric Environments

Abstract

Recent state-of-the-art artificial agents lack the ability to adapt rapidly to new tasks, as they are trained exclusively for specific objectives and require massive amounts of interaction to learn new skills. Meta-reinforcement learning (meta-RL) addresses this challenge by leveraging knowledge learned from training tasks to perform well in previously unseen tasks. However, current meta-RL approaches limit themselves to narrow parametric task distributions, ignoring qualitative differences between tasks that occur in the real world. In this paper, we introduce TIGR, a Task-Inference-based meta-RL algorithm using Gaussian mixture models (GMM) and gated Recurrent units, designed for tasks in non-parametric environments. We employ a generative model involving a GMM to capture the multi-modality of the tasks. We decouple the policy training from the task-inference learning and efficiently train the inference mechanism on the basis of an unsupervised reconstruction objective. We provide a benchmark with qualitatively distinct tasks based on the half-cheetah environment and demonstrate the superior performance of TIGR compared to state-of-the-art meta-RL approaches in terms of sample efficiency (3-10 times faster), asymptotic performance, and applicability in non-parametric environments with zero-shot adaptation.

References in corpus (6)

• Solving Rubik's Cube with a Robot Hand
• Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders
• Learning to reinforcement learn
• Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables
• Continual Unsupervised Representation Learning
• Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL