Add to ORKGAbstract. In this paper, we introduce a probabilistic version of the well-studied Value-Iteration approach, i.e. Probabilistic Value-Iteration (PVI). The PVI approach can handle continuous states and actions in an episodic Reinforcement Learning (RL) setting, while using Gaussian Processes to model the state uncertainties. We further show, how the approach can be efficiently realized making it suitable for learning with large data. The proposed PVI is evaluated on a benchmark problem, as well as on a real robot for learning a control task. A comparison of PVI with two state-of-the-art RL algorithms shows that the proposed approach is competitive in performance while being efficient in learning.
We provide a novel framework for very fast model-based reinforcement learning in continuous state an...
We consider the problem of reinforcement learning with an orientation toward contexts in which an ag...
We present a model-free reinforcement learning algorithm to synthesize control policies that maximiz...
Reinforcement learning (RL) and optimal control of systems with contin- uous states and actions requ...
Abstract—Autonomous learning has been a promising direction in control and robotics for more than a ...
Abstract—Autonomous learning has been a promising direction in control and robotics for more than a ...
Optimal control and Reinforcement Learning deal both with sequential decision-making problems, altho...
Autonomous learning has been a promising direction in control and robotics for more than a decade si...
We consider the model-based reinforcement learning framework where we are interested in learning a m...
The dilemma between exploration and exploitation is an important topic in reinforcement learning (RL...
Model-free reinforcement learning based methods such as Proximal Policy Optimization, or Q-learning ...
Dynamic control tasks are good candidates for the application of reinforcement learning techniques. ...
tion and the use of Gaussian Processes. They belong to the class of fitted value iteration algorithm...
Thesis (Ph.D.)--University of Washington, 2020Informed and robust decision making in the face of unc...
Probabilistic inference is at the core of many recent advances in machine learning. Unfortunately, ...
We provide a novel framework for very fast model-based reinforcement learning in continuous state an...
We consider the problem of reinforcement learning with an orientation toward contexts in which an ag...
We present a model-free reinforcement learning algorithm to synthesize control policies that maximiz...
Reinforcement learning (RL) and optimal control of systems with contin- uous states and actions requ...
Abstract—Autonomous learning has been a promising direction in control and robotics for more than a ...
Abstract—Autonomous learning has been a promising direction in control and robotics for more than a ...
Optimal control and Reinforcement Learning deal both with sequential decision-making problems, altho...
Autonomous learning has been a promising direction in control and robotics for more than a decade si...
We consider the model-based reinforcement learning framework where we are interested in learning a m...
The dilemma between exploration and exploitation is an important topic in reinforcement learning (RL...
Model-free reinforcement learning based methods such as Proximal Policy Optimization, or Q-learning ...
Dynamic control tasks are good candidates for the application of reinforcement learning techniques. ...
tion and the use of Gaussian Processes. They belong to the class of fitted value iteration algorithm...
Thesis (Ph.D.)--University of Washington, 2020Informed and robust decision making in the face of unc...
Probabilistic inference is at the core of many recent advances in machine learning. Unfortunately, ...
We provide a novel framework for very fast model-based reinforcement learning in continuous state an...
We consider the problem of reinforcement learning with an orientation toward contexts in which an ag...
We present a model-free reinforcement learning algorithm to synthesize control policies that maximiz...