Sciweavers

86 search results - page 16 / 18
» Evolution of reward functions for reinforcement learning
Sort
View
JMLR
2010
119views more  JMLR 2010»
14 years 6 months ago
A Convergent Online Single Time Scale Actor Critic Algorithm
Actor-Critic based approaches were among the first to address reinforcement learning in a general setting. Recently, these algorithms have gained renewed interest due to their gen...
Dotan Di Castro, Ron Meir
ICML
1996
IEEE
16 years 13 days ago
Learning Evaluation Functions for Large Acyclic Domains
Some of the most successful recent applications of reinforcement learning have used neural networks and the TD algorithm to learn evaluation functions. In this paper, we examine t...
Justin A. Boyan, Andrew W. Moore
ICANN
1997
Springer
15 years 3 months ago
On Learning Soccer Strategies
We use simulated soccer to study multiagent learning. Each team's players (agents) share action set and policy but may behave differently due to position-dependent inputs. All...
Rafal Salustowicz, Marco Wiering, Jürgen Schm...
AROBOTS
1999
87views more  AROBOTS 1999»
14 years 11 months ago
Dynamics of a Classical Conditioning Model
Abstract. Classical conditioning is a basic learning mechanism in animals and can be found in almost all organisms. If we want to construct robots with abilities matching those of ...
Christian Balkenius
ICML
1994
IEEE
15 years 3 months ago
A Modular Q-Learning Architecture for Manipulator Task Decomposition
Compositional Q-Learning (CQ-L) (Singh 1992) is a modular approach to learning to performcomposite tasks made up of several elemental tasks by reinforcement learning. Skills acqui...
Chen K. Tham, Richard W. Prager