papers AI Learner
The Github is limit! Click to go to the new site.

Adaptive Guidance with Reinforcement Meta-Learning

2019-01-12
Brian Gaudet, Richard Linares

Abstract

This paper proposes a novel adaptive guidance system developed using reinforcement meta-learning with a recurrent policy and value function approximator. The use of recurrent network layers allows the deployed policy to adapt real time to environmental forces acting on the agent. We compare the performance of the DR/DV guidance law, an RL agent with a non-recurrent policy, and an RL agent with a recurrent policy in four difficult tasks with unknown but highly variable dynamics. These tasks include a safe Mars landing with random engine failure and a landing on an asteroid with unknown environmental dynamics. We also demonstrate the ability of a recurrent policy to navigate using only Doppler radar altimeter returns, thus integrating guidance and navigation.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1901.04473

PDF

http://arxiv.org/pdf/1901.04473


Comments

Content