Sciweavers

HEURISTICS
2008
170views more  HEURISTICS 2008»
13 years 3 months ago
Accelerating autonomous learning by using heuristic selection of actions
This paper investigates how to make improved action selection for online policy learning in robotic scenarios using reinforcement learning (RL) algorithms. Since finding control po...
Reinaldo A. C. Bianchi, Carlos H. C. Ribeiro, Anna...
ECAI
2010
Springer
13 years 4 months ago
The Dynamics of Multi-Agent Reinforcement Learning
Abstract. Infinite-horizon multi-agent control processes with nondeterminism and partial state knowledge have particularly interesting properties with respect to adaptive control, ...
Luke Dickens, Krysia Broda, Alessandra Russo
ATAL
2008
Springer
13 years 5 months ago
Expediting RL by using graphical structures
The goal of Reinforcement learning (RL) is to maximize reward (minimize cost) in a Markov decision process (MDP) without knowing the underlying model a priori. RL algorithms tend ...
Peng Dai, Alexander L. Strehl, Judy Goldsmith
WSC
2008
13 years 6 months ago
On step sizes, stochastic shortest paths, and survival probabilities in Reinforcement Learning
Reinforcement Learning (RL) is a simulation-based technique useful in solving Markov decision processes if their transition probabilities are not easily obtainable or if the probl...
Abhijit Gosavi
ATAL
2003
Springer
13 years 9 months ago
A selection-mutation model for q-learning in multi-agent systems
Although well understood in the single-agent framework, the use of traditional reinforcement learning (RL) algorithms in multi-agent systems (MAS) is not always justified. The fe...
Karl Tuyls, Katja Verbeeck, Tom Lenaerts
ICML
2003
IEEE
14 years 4 months ago
TD(0) Converges Provably Faster than the Residual Gradient Algorithm
In Reinforcement Learning (RL) there has been some experimental evidence that the residual gradient algorithm converges slower than the TD(0) algorithm. In this paper, we use the ...
Ralf Schoknecht, Artur Merke
ICML
2004
IEEE
14 years 4 months ago
Convergence of synchronous reinforcement learning with linear function approximation
Synchronous reinforcement learning (RL) algorithms with linear function approximation are representable as inhomogeneous matrix iterations of a special form (Schoknecht & Merk...
Artur Merke, Ralf Schoknecht
ICML
2006
IEEE
14 years 4 months ago
An analytic solution to discrete Bayesian reinforcement learning
Reinforcement learning (RL) was originally proposed as a framework to allow agents to learn in an online fashion as they interact with their environment. Existing RL algorithms co...
Pascal Poupart, Nikos A. Vlassis, Jesse Hoey, Kevi...