Add to ORKGHierarchical methods have attracted much recent attention as a means for scaling reinforcement learning algorithms to in-creasingly complex, real-world tasks. These methods pro-vide two important kinds of abstraction that facilitate learn-ing. First, hierarchies organize actions into temporally ab-stract high-level tasks. Second, they facilitate task dependent state abstractions that allow each high-level task to restrict at-tention only to relevant state variables. In most approaches to date, the user must supply suitable task decompositions and state abstractions to the learner. How to discover these hi-erarchies automatically remains a challenging open problem. As a first step towards solving this problem, we introduce a general method f...
Hierarchical Reinforcement Learning (HRL) algorithms can perform planning at multiple levels of abst...
Common approaches to Reinforcement Learning (RL) are seriously challenged by large-scale application...
Reinforcement learning (RL) is an area of Machine Learning (ML) concerned with learning how a softwa...
Safe state abstraction in reinforcement learning allows an agent to ignore aspects of its current st...
Reinforcement learning presents a challenging problem: agents must generalize experiences, efficient...
Reinforcement learning provides a means for autonomous agents to improve their action selection stra...
To operate effectively in complex environments learning agents require the ability to form useful ab...
This paper presents a new method for the autonomous construction of hierarchical action and state re...
This thesis addresses the open problem of automatically discovering hierarchical structure in reinfo...
State abstractions are often used to reduce the complexity of model-based reinforcement learn-ing wh...
This paper introduces a novel approach for abstraction selection in reinforcement learning problems ...
The contribution of this paper is to introduce heuristics, that go beyond safe state abstraction in ...
Abstract. Reinforcement learning is bedeviled by the curse of dimensionality: the number of paramete...
Humans use prior knowledge to efficiently solve novel tasks, but how they structure past knowledge d...
Hierarchical reinforcement learning has focused on discovering temporally extended actions (options)...
Hierarchical Reinforcement Learning (HRL) algorithms can perform planning at multiple levels of abst...
Common approaches to Reinforcement Learning (RL) are seriously challenged by large-scale application...
Reinforcement learning (RL) is an area of Machine Learning (ML) concerned with learning how a softwa...
Safe state abstraction in reinforcement learning allows an agent to ignore aspects of its current st...
Reinforcement learning presents a challenging problem: agents must generalize experiences, efficient...
Reinforcement learning provides a means for autonomous agents to improve their action selection stra...
To operate effectively in complex environments learning agents require the ability to form useful ab...
This paper presents a new method for the autonomous construction of hierarchical action and state re...
This thesis addresses the open problem of automatically discovering hierarchical structure in reinfo...
State abstractions are often used to reduce the complexity of model-based reinforcement learn-ing wh...
This paper introduces a novel approach for abstraction selection in reinforcement learning problems ...
The contribution of this paper is to introduce heuristics, that go beyond safe state abstraction in ...
Abstract. Reinforcement learning is bedeviled by the curse of dimensionality: the number of paramete...
Humans use prior knowledge to efficiently solve novel tasks, but how they structure past knowledge d...
Hierarchical reinforcement learning has focused on discovering temporally extended actions (options)...
Hierarchical Reinforcement Learning (HRL) algorithms can perform planning at multiple levels of abst...
Common approaches to Reinforcement Learning (RL) are seriously challenged by large-scale application...
Reinforcement learning (RL) is an area of Machine Learning (ML) concerned with learning how a softwa...