Safe, efficient, and comfortable velocity control based on reinforcement learning for autonomous driving

M Zhu, Y Wang, Z Pu, J Hu, X Wang, R Ke - Transportation Research Part …, 2020 - Elsevier
… a car-following model for autonomous velocity control based on reinforcement learning (RL)…
This model directly optimizes driving safety, efficiency, and comfort, by learning from …

Data-efficient reinforcement learning with self-predictive representations

M Schwarzer, A Anand, R Goel, RD Hjelm… - arXiv preprint arXiv …, 2020 - arxiv.org
… We show that data augmentation can be more effectively leveraged in reinforcement
learning by forcing representations to be consistent between different augmented views of an …

Deep reinforcement learning

SE Li - Reinforcement learning for sequential decision and …, 2023 - Springer
… in DRL and is often accompanied by severely low efficiency. One common strategy to eliminate
… We use the following update rule to demonstrate how the overestimation issue occurs: …

Human-level performance in 3D multiplayer games with population-based reinforcement learning

M Jaderberg, WM Czarnecki, I Dunning, L Marris… - Science, 2019 - science.org
… sparse to be effectively used as the … through training. Opponent base camping (red) is
discovered early on, whereas teammate following (blue) becomes very prominent midway through

Training a helpful and harmless assistant with reinforcement learning from human feedback

Y Bai, A Jones, K Ndousse, A Askell, A Chen… - arXiv preprint arXiv …, 2022 - arxiv.org
… a weekly cadence with fresh human feedback data, efficiently improving our datasets and …
improving general-purpose instruction following). We also find that mixing preference model …

Advanced planning for autonomous vehicles using reinforcement learning and deep inverse reinforcement learning

C You, J Lu, D Filev, P Tsiotras - Robotics and Autonomous Systems, 2019 - Elsevier
… the same time, increase fuel efficiency and reduce congestion. … autonomous vehicle using
reinforcement learning techniques. … following, we formulate the inverse reinforcement learning

Crowd-robot interaction: Crowd-aware robot navigation with attention-based deep reinforcement learning

C Chen, Y Liu, S Kreiss, A Alahi - … international conference on …, 2019 - ieeexplore.ieee.org
… Our model captures the Human-Human interactions occurring in dense crowds that … following
sections, we will present a novel Crowd-Robot Interaction model that can effectively learn

Dynamical hyperparameter optimization via deep reinforcement learning in tracking

X Dong, J Shen, W Wang, L Shao… - … analysis and machine …, 2019 - ieeexplore.ieee.org
… To overcome this challenge, we introduce an efficient heuristic strategy to handle high
dimensional state space, while also accelerating the convergence behavior. The proposed …

Residual reinforcement learning for robot control

T Johannink, S Bahl, A Nair, J Luo… - … on robotics and …, 2019 - ieeexplore.ieee.org
… and the computed torque method, usually follow predefined trajectories with little adaptive
… can solve tasks such as path following efficiently, applications that involve contacts between …

Survey of deep reinforcement learning for motion planning of autonomous vehicles

S Aradi - IEEE Transactions on Intelligent Transportation …, 2020 - ieeexplore.ieee.org
… usually use DRL to define splines as a result of the training [… lanekeeping, trajectory following,
or car following is the higher… deep reinforcement learning techniques could be effectively