A survey on model-based reinforcement learning

FM Luo, T Xu, H Lai, XH Chen, W Zhang… - Science China Information …, 2024‏ - Springer
Reinforcement learning (RL) interacts with the environment to solve sequential decision-
making problems via a trial-and-error approach. Errors are always undesirable in real-world …

Variable impedance control and learning—a review

FJ Abu-Dakka, M Saveriano - Frontiers in Robotics and AI, 2020‏ - frontiersin.org
Robots that physically interact with their surroundings, in order to accomplish some tasks or
assist humans in their activities, require to exploit contact forces in a safe and proficient …

Morel: Model-based offline reinforcement learning

R Kidambi, A Rajeswaran… - Advances in neural …, 2020‏ - proceedings.neurips.cc
In offline reinforcement learning (RL), the goal is to learn a highly rewarding policy based
solely on a dataset of historical interactions with the environment. This serves as an extreme …

[كتاب][B] Machine learning in finance

MF Dixon, I Halperin, P Bilokon - 2020‏ - Springer
Machine learning in finance sits at the intersection of a number of emergent and established
disciplines including pattern recognition, financial econometrics, statistical computing …

Model-based reinforcement learning: A survey

TM Moerland, J Broekens, A Plaat… - … and Trends® in …, 2023‏ - nowpublishers.com
Sequential decision making, commonly formalized as Markov Decision Process (MDP)
optimization, is an important challenge in artificial intelligence. Two key approaches to this …

Optimization-based control for dynamic legged robots

PM Wensing, M Posa, Y Hu, A Escande… - IEEE Transactions …, 2023‏ - ieeexplore.ieee.org
In a world designed for legs, quadrupeds, bipeds, and humanoids have the opportunity to
impact emerging robotics applications from logistics, to agriculture, to home assistance. The …

A unified mpc framework for whole-body dynamic locomotion and manipulation

JP Sleiman, F Farshidian, MV Minniti… - IEEE Robotics and …, 2021‏ - ieeexplore.ieee.org
In this letter, we propose a whole-body planning framework that unifies dynamic locomotion
and manipulation tasks by formulating a single multi-contact optimal control problem. We …

Global convergence of policy gradient methods for the linear quadratic regulator

M Fazel, R Ge, S Kakade… - … conference on machine …, 2018‏ - proceedings.mlr.press
Direct policy gradient methods for reinforcement learning and continuous control problems
are a popular approach for a variety of reasons: 1) they are easy to implement without …

Local motion phases for learning multi-contact character movements

S Starke, Y Zhao, T Komura, K Zaman - ACM Transactions on Graphics …, 2020‏ - dl.acm.org
Training a bipedal character to play basketball and interact with objects, or a quadruped
character to move in various locomotion modes, are difficult tasks due to the fast and …

Solar: Deep structured representations for model-based reinforcement learning

M Zhang, S Vikram, L Smith, P Abbeel… - International …, 2019‏ - proceedings.mlr.press
Abstract Model-based reinforcement learning (RL) has proven to be a data efficient
approach for learning control tasks but is difficult to utilize in domains with complex …