textHow can an agent bootstrap up from a pixel-level representation to autonomously learn high-level states and actions using only domain general knowledge? This thesis attacks a piece of this problem and assumes that an agent has a set of continuous variables describing the environment and a set of continuous motor primitives, and poses a solution for the problem of how an agent can learn a set of useful states and effective higher-level actions through autonomous experience with the environment. There exist methods for learning models of the environment, and there also exist methods for planning. However, for autonomous learning, these methods have been used almost exclusively in discrete environments. This thesis proposes attacking th...
We present a method that allows an agent to learn a qualitative state representation that can be app...
AbstractThis paper presents a set of methods by which a learning agent can learn a sequence of incre...
Decades of AI research have yielded techniques for learn-ing, inference, and planning that depend on...
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...
There has been intense interest in hierarchical rein-forcement learning as a way to make Markov de-c...
Abstract—An embodied agent senses the world at the pixel level through a large number of sense eleme...
We consider the problem of how a learn-ing agent in a continuous and dynamic world can autonomously ...
We consider the problem of how a learning agent in a continuous and dynamic world can autonomously l...
Among the most impressive of aspects of human intelligence is skill acquisition—the ability to ident...
We consider the problem of how a learn-ing agent in a continuous and dynamic world can autonomously ...
My research activity focuses on the integration of acting, learning and planning. The main objective...
To be autonomous, intelligent robots must learn the foundations of commonsense knowledge from their ...
Applications of learning to autonomous agents (simulated or real) have often been restricted to lear...
Applications of learning to autonomous agents (simulated or real) have often been restricted to lear...
We present a method that allows an agent to learn a qualitative state representation that can be app...
AbstractThis paper presents a set of methods by which a learning agent can learn a sequence of incre...
Decades of AI research have yielded techniques for learn-ing, inference, and planning that depend on...
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...
There has been intense interest in hierarchical rein-forcement learning as a way to make Markov de-c...
Abstract—An embodied agent senses the world at the pixel level through a large number of sense eleme...
We consider the problem of how a learn-ing agent in a continuous and dynamic world can autonomously ...
We consider the problem of how a learning agent in a continuous and dynamic world can autonomously l...
Among the most impressive of aspects of human intelligence is skill acquisition—the ability to ident...
We consider the problem of how a learn-ing agent in a continuous and dynamic world can autonomously ...
My research activity focuses on the integration of acting, learning and planning. The main objective...
To be autonomous, intelligent robots must learn the foundations of commonsense knowledge from their ...
Applications of learning to autonomous agents (simulated or real) have often been restricted to lear...
Applications of learning to autonomous agents (simulated or real) have often been restricted to lear...
We present a method that allows an agent to learn a qualitative state representation that can be app...
AbstractThis paper presents a set of methods by which a learning agent can learn a sequence of incre...
Decades of AI research have yielded techniques for learn-ing, inference, and planning that depend on...