Add to ORKGThis thesis studies the problem of learning a model in Model-Based Reinforcement Learning (MBRL). We consider model classes that do not contain a perfect model of the underlying environment, and suggest that model learning should be closely related to how the model will be used. We examine how the planning module of an MBRL algorithm uses the model, and propose that the model learning module should incorporate the way the planner is going to use the model. This is in contrast to conventional model learning approaches that learn a predictive model of the environment without explicitly considering the interaction of the model and the planner. We focus on policy gradient planning algorithms and derive new loss functions for model learning whic...
Model-based Reinforcement Learning (MBRL) holds promise for data-efficiency by planning with model-g...
We present a model-free reinforcement learning method for partially observable Markov decision probl...
Model-based reinforcement learning methods make efficient use of samples by building a model of the ...
This thesis studies the problem of learning a model in Model-Based Reinforcement Learning (MBRL). We...
Traditional model-based reinforcement learning approaches learn a model of the environment dynamics ...
The goal of reinforcement learning (RL) is to let an agent learn an optimal control policy in an unk...
Policy gradient methods are a type of reinforcement learning techniques that rely upon optimizing pa...
Model-based reinforcement learning algorithms have been shown to achieve successful results on vario...
Model-based reinforcement learning, in which a model of the environment's dynamics is learned a...
Much of the focus on finding good representations in reinforcement learning has been on learning com...
We introduce and empirically evaluate two novel online gradient-based reinforcement learning algorit...
A policy gradient method is a reinforcement learning approach that directly optimizes a parametrized...
Deep reinforcement learning methods are capable of learning complex heuristics starting with no prio...
Thesis (Ph.D.)--University of Washington, 2022Sequential decision making, especially in the face of ...
Model-based reinforcement learning (MBRL) has often been touted for its potential to improve on the ...
Model-based Reinforcement Learning (MBRL) holds promise for data-efficiency by planning with model-g...
We present a model-free reinforcement learning method for partially observable Markov decision probl...
Model-based reinforcement learning methods make efficient use of samples by building a model of the ...
This thesis studies the problem of learning a model in Model-Based Reinforcement Learning (MBRL). We...
Traditional model-based reinforcement learning approaches learn a model of the environment dynamics ...
The goal of reinforcement learning (RL) is to let an agent learn an optimal control policy in an unk...
Policy gradient methods are a type of reinforcement learning techniques that rely upon optimizing pa...
Model-based reinforcement learning algorithms have been shown to achieve successful results on vario...
Model-based reinforcement learning, in which a model of the environment's dynamics is learned a...
Much of the focus on finding good representations in reinforcement learning has been on learning com...
We introduce and empirically evaluate two novel online gradient-based reinforcement learning algorit...
A policy gradient method is a reinforcement learning approach that directly optimizes a parametrized...
Deep reinforcement learning methods are capable of learning complex heuristics starting with no prio...
Thesis (Ph.D.)--University of Washington, 2022Sequential decision making, especially in the face of ...
Model-based reinforcement learning (MBRL) has often been touted for its potential to improve on the ...
Model-based Reinforcement Learning (MBRL) holds promise for data-efficiency by planning with model-g...
We present a model-free reinforcement learning method for partially observable Markov decision probl...
Model-based reinforcement learning methods make efficient use of samples by building a model of the ...