no code implementations • 14 Mar 2018 • Carl-Johan Hoel, Krister Wolff, Leo Laine
This paper introduces a method, based on deep reinforcement learning, for automatically generating a general purpose decision making function.
no code implementations • 6 May 2019 • Carl-Johan Hoel, Katherine Driggs-Campbell, Krister Wolff, Leo Laine, Mykel J. Kochenderfer
This paper introduces a general framework for tactical decision making, which combines the concepts of planning and learning, in the form of Monte Carlo tree search and deep reinforcement learning.
1 code implementation • 22 Apr 2020 • Carl-Johan Hoel, Krister Wolff, Leo Laine
This paper investigates how a Bayesian RL technique, based on an ensemble of neural networks with additional randomized prior functions (RPF), can be used to estimate the uncertainty of decisions in autonomous driving.
no code implementations • 17 Jun 2020 • Carl-Johan Hoel, Tommy Tram, Jonas Sjöberg
This paper investigates how a Bayesian reinforcement learning method can be used to create a tactical decision-making agent for autonomous driving in an intersection scenario, where the agent can estimate the confidence of its recommended actions.
1 code implementation • 21 May 2021 • Carl-Johan Hoel, Krister Wolff, Leo Laine
The distribution over returns is estimated by learning its quantile function implicitly, which gives the aleatoric uncertainty, whereas an ensemble of agents is trained on bootstrapped data to provide a Bayesian estimation of the epistemic uncertainty.