Action modeling is an important skill for agents that must perform tasks in novel domains. Previous work on action modeling has focused on learning STRIPS operators in discrete, relational domains. There has also been a separate vein of work in continuous function approximation for use in optimal control in robotics. Most real world domains are grounded in continuous dynamics but also exhibit emergent regularities at an abstract relational level of description. These two levels of regularity are often difficult to capture using a single action representation and learning method. In this paper we describe a system that combines discrete and continuous action modeling techniques in the Soar cognitive architecture. Our system accepts a continu...
We present a method that allows an agent to learn a qualitative state representation that can be app...
In this paper we test two coordination methods – difference rewards and coordination graphs – in a c...
Reinforcement learning algorithms have proven to be capable of solving complicated robotics tasks in...
Long-living autonomous agents must be able to learn to perform competently in novel environments. On...
Long-living autonomous agents must be able to learn to perform competently in novel environments. O...
We present an instance-based, online method for learning action models in unanticipated, relational ...
Although several researchers have integrated methods for re-inforcement learning (RL) with case-base...
textHow can an agent bootstrap up from a pixel-level representation to autonomously learn high-level...
How can an agent bootstrap up from a pixel-level representation to autonomously learn high-level sta...
International audienceWe present a novel approach to state space discretization for constructivist a...
Reinforcement Learning is a commonly used technique for learning tasks in robotics, however, traditi...
Summarization: The majority of learning algorithms available today focus on approximating the state ...
Summarization: Reinforcement Learning methods for controlling stochastic processes typically assume ...
There has been intense interest in hierarchical rein-forcement learning as a way to make Markov de-c...
Dynamic control tasks are good candidates for the application of reinforcement learning techniques. ...
We present a method that allows an agent to learn a qualitative state representation that can be app...
In this paper we test two coordination methods – difference rewards and coordination graphs – in a c...
Reinforcement learning algorithms have proven to be capable of solving complicated robotics tasks in...
Long-living autonomous agents must be able to learn to perform competently in novel environments. On...
Long-living autonomous agents must be able to learn to perform competently in novel environments. O...
We present an instance-based, online method for learning action models in unanticipated, relational ...
Although several researchers have integrated methods for re-inforcement learning (RL) with case-base...
textHow can an agent bootstrap up from a pixel-level representation to autonomously learn high-level...
How can an agent bootstrap up from a pixel-level representation to autonomously learn high-level sta...
International audienceWe present a novel approach to state space discretization for constructivist a...
Reinforcement Learning is a commonly used technique for learning tasks in robotics, however, traditi...
Summarization: The majority of learning algorithms available today focus on approximating the state ...
Summarization: Reinforcement Learning methods for controlling stochastic processes typically assume ...
There has been intense interest in hierarchical rein-forcement learning as a way to make Markov de-c...
Dynamic control tasks are good candidates for the application of reinforcement learning techniques. ...
We present a method that allows an agent to learn a qualitative state representation that can be app...
In this paper we test two coordination methods – difference rewards and coordination graphs – in a c...
Reinforcement learning algorithms have proven to be capable of solving complicated robotics tasks in...