[PDF][PDF] Policy learning with constraints in model-free reinforcement learning: A survey

Y Liu, A Halev, X Liu - The 30th international joint conference on artificial …, 2021 - par.nsf.gov
Reinforcement Learning (RL) algorithms have had tremendous success in simulated
domains. These algorithms, however, often cannot be directly applied to physical systems …

Understanding the impact of entropy on policy optimization

Z Ahmed, N Le Roux, M Norouzi… - … on machine learning, 2019 - proceedings.mlr.press
Entropy regularization is commonly used to improve policy optimization in reinforcement
learning. It is believed to help with exploration by encouraging the selection of more …

Learning robust autonomous navigation and locomotion for wheeled-legged robots

J Lee, M Bjelonic, A Reske, L Wellhausen, T Miki… - Science Robotics, 2024 - science.org
Autonomous wheeled-legged robots have the potential to transform logistics systems,
improving operational efficiency and adaptability in urban environments. Navigating urban …

Applying deep reinforcement learning to active flow control in weakly turbulent conditions

F Ren, J Rabault, H Tang - Physics of Fluids, 2021 - pubs.aip.org
Machine learning has recently become a promising technique in fluid mechanics, especially
for active flow control (AFC) applications. A recent work [Rabault et al., J. Fluid Mech. 865 …

Reinforcement learning for batch bioprocess optimization

P Petsagkourakis, IO Sandoval, E Bradford… - Computers & Chemical …, 2020 - Elsevier
Bioprocesses have received a lot of attention to produce clean and sustainable alternatives
to fossil-based materials. However, they are generally difficult to optimize due to their …

Health-considered energy management strategy for fuel cell hybrid electric vehicle based on improved soft actor critic algorithm adopted with Beta policy

W Chen, J Peng, J Chen, J Zhou, Z Wei… - Energy Conversion and …, 2023 - Elsevier
Deep reinforcement learning-based energy management strategy (EMS) is essential for fuel
cell hybrid electric vehicles to reduce hydrogen consumption, improve health performance …

Automated reinforcement learning: An overview

RR Afshar, Y Zhang, J Vanschoren… - arXiv preprint arXiv …, 2022 - arxiv.org
Reinforcement Learning and recently Deep Reinforcement Learning are popular methods
for solving sequential decision making problems modeled as Markov Decision Processes …

Keeping your distance: Solving sparse reward tasks using self-balancing shaped rewards

A Trott, S Zheng, C Xiong… - Advances in Neural …, 2019 - proceedings.neurips.cc
While using shaped rewards can be beneficial when solving sparse reward tasks, their
successful application often requires careful engineering and is problem specific. For …

Action space shaping in deep reinforcement learning

A Kanervisto, C Scheller… - 2020 IEEE conference on …, 2020 - ieeexplore.ieee.org
Reinforcement learning (RL) has been successful in training agents in various learning
environments, including video games. However, such work modifies and shrinks the action …

Driving in dense traffic with model-free reinforcement learning

DM Saxena, S Bae, A Nakhaei… - … on Robotics and …, 2020 - ieeexplore.ieee.org
Traditional planning and control methods could fail to find a feasible trajectory for an
autonomous vehicle to execute amongst dense traffic on roads. This is because the obstacle …