DeepAI AI Chat
Log In Sign Up

Few-shot model-based adaptation in noisy conditions

by   Karol Arndt, et al.

Few-shot adaptation is a challenging problem in the context of simulation-to-real transfer in robotics, requiring safe and informative data collection. In physical systems, additional challenge may be posed by domain noise, which is present in virtually all real-world applications. In this paper, we propose to perform few-shot adaptation of dynamics models in noisy conditions using an uncertainty-aware Kalman filter-based neural network architecture. We show that the proposed method, which explicitly addresses domain noise, improves few-shot adaptation error over a blackbox adaptation LSTM baseline, and over a model-free on-policy reinforcement learning approach, which tries to learn an adaptable and informative policy at the same time. The proposed method also allows for system analysis by analyzing hidden states of the model during and after adaptation.


page 1

page 5

page 6


Domain Curiosity: Learning Efficient Data Collection Strategies for Domain Adaptation

Domain adaptation is a common problem in robotics, with applications suc...

Sequential Learning from Noisy Data: Data-Assimilation Meets Echo-State Network

This paper explores the problem of training a recurrent neural network f...

Unsupervised Learned Kalman Filtering

In this paper we adapt KalmanNet, which is a recently pro-posed deep neu...

Meta Reinforcement Learning for Sim-to-real Domain Adaptation

Modern reinforcement learning methods suffer from low sample efficiency ...

Reinforcement Learning for Few-Shot Text Generation Adaptation

Controlling the generative model to adapt a new domain with limited samp...

Zero-Shot Reinforcement Learning on Graphs for Autonomous Exploration Under Uncertainty

This paper studies the problem of autonomous exploration under localizat...