AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning
arXiv:2107.02729
Abstract
One practical challenge in reinforcement learning (RL) is how to make quick adaptations when faced with new environments. In this paper, we propose a principled framework for adaptive RL, called \textit{AdaRL}, that adapts reliably and efficiently to changes across domains with a few samples from the target domain, even in partially observable environments. Specifically, we leverage a parsimonious graphical representation that characterizes structural relationships over variables in the RL system. Such graphical representations provide a compact way to encode what and where the changes across domains are, and furthermore inform us with a minimal set of changes that one has to consider for the purpose of policy adaptation. We show that by explicitly leveraging this compact representation to encode changes, we can efficiently adapt the policy to the target domain, in which only a few samples are needed and further policy optimization is avoided. We illustrate the efficacy of AdaRL through a series of experiments that vary factors in the observation, transition, and reward functions for Cartpole and Atari games.
References in corpus (16)
- Auto-Encoding Variational Bayes
- Continuous control with deep reinforcement learning
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Playing Atari with Deep Reinforcement Learning
- High-Dimensional Continuous Control Using Generalized Advantage Estimation
- Kernel-based Conditional Independence Test and Application in Causal Discovery
- Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables
- Fast Context Adaptation via Meta-Learning
- Transfer Learning in Deep Reinforcement Learning: A Survey
- Causality for Machine Learning
- A PAC-Bayesian bound for Lifelong Learning
- Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theory
- Learning Invariant Representations for Reinforcement Learning without Reconstruction
- Hidden Parameter Markov Decision Processes: A Semiparametric Regression Approach for Discovering Latent Task Parametrizations
- Importance Weighted Transfer of Samples in Reinforcement Learning
- Domain Adaptation as a Problem of Inference on Graphical Models