[PDF][PDF] Policy learning with constraints in model-free reinforcement learning: A survey
Reinforcement Learning (RL) algorithms have had tremendous success in simulated
domains. These algorithms, however, often cannot be directly applied to physical systems …
domains. These algorithms, however, often cannot be directly applied to physical systems …
Understanding the impact of entropy on policy optimization
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. It is believed to help with exploration by encouraging the selection of more …
Learning robust autonomous navigation and locomotion for wheeled-legged robots
Autonomous wheeled-legged robots have the potential to transform logistics systems,
improving operational efficiency and adaptability in urban environments. Navigating urban …
improving operational efficiency and adaptability in urban environments. Navigating urban …
Applying deep reinforcement learning to active flow control in weakly turbulent conditions
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 …
for active flow control (AFC) applications. A recent work [Rabault et al., J. Fluid Mech. 865 …
Reinforcement learning for batch bioprocess optimization
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 …
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
Deep reinforcement learning-based energy management strategy (EMS) is essential for fuel
cell hybrid electric vehicles to reduce hydrogen consumption, improve health performance …
cell hybrid electric vehicles to reduce hydrogen consumption, improve health performance …
Automated reinforcement learning: An overview
Reinforcement Learning and recently Deep Reinforcement Learning are popular methods
for solving sequential decision making problems modeled as Markov Decision Processes …
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 …
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 …
environments, including video games. However, such work modifies and shrinks the action …
Driving in dense traffic with model-free reinforcement learning
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 …
autonomous vehicle to execute amongst dense traffic on roads. This is because the obstacle …