Sciweavers

99 search results - page 1 / 20
» Software agents that learn through observation
Sort
View
ATAL
2006
Springer
13 years 8 months ago
Software agents that learn through observation
In this paper, we present an architecture for software agents that enables them to learn vocabulary through the observation of each other bodies and actions. Besides sensors, effe...
Jaçanã Machado, Luís Miguel B...
ICRA
2010
IEEE
147views Robotics» more  ICRA 2010»
13 years 3 months ago
Learning physically-instantiated game play through visual observation
Abstract— We present an integrated vision and robotic system that plays, and learns to play, simple physically-instantiated board games that are variants of TIC TAC TOE and HEXAP...
Andrei Barbu, Siddharth Narayanaswamy, Jeffrey Mar...
ATAL
2006
Springer
13 years 8 months ago
Learning executable agent behaviors from observation
We present a method for learning a human understandable, executable model of an agent's behavior using observations of its interaction with the environment. By executable we ...
Andrew Guillory, Hai Nguyen, Tucker R. Balch, Char...
BIOADIT
2004
Springer
13 years 10 months ago
Autonomous Acquisition of the Meaning of Sensory States Through Sensory-Invariance Driven Action
Abstract. How can artificial or natural agents autonomously gain understanding of its own internal (sensory) state? This is an important question not just for physically embodied ...
Yoonsuck Choe, S. Kumar Bhamidipati
CORR
2011
Springer
194views Education» more  CORR 2011»
12 years 8 months ago
Accelerating Reinforcement Learning through Implicit Imitation
Imitation can be viewed as a means of enhancing learning in multiagent environments. It augments an agent’s ability to learn useful behaviors by making intelligent use of the kn...
Craig Boutilier, Bob Price