Sciweavers

Share

Publication
160views
5 years 6 months ago
ABC Reinforcement Learning
This paper introduces a simple, general framework for likelihood-free Bayesian reinforcement learning, through Approximate Bayesian Computation (ABC). The main advantage is th...
Christos Dimitrakakis, Nikolaos Tziortziotis

Publication
130views
5 years 6 months ago
Linear Bayesian Reinforcement Learning
This paper proposes a simple linear Bayesian approach to reinforcement learning. We show that with an appropriate basis, a Bayesian linear Gaussian model is sufficient for accurat...
Nikolaos Tziortziotis and Christos Dimitrakakis
AAAI
2012
6 years 5 months ago
Competing with Humans at Fantasy Football: Team Formation in Large Partially-Observable Domains
We present the first real-world benchmark for sequentiallyoptimal team formation, working within the framework of a class of online football prediction games known as Fantasy Foo...
Tim Matthews, Sarvapali D. Ramchurn, Georgios Chal...
CORR
2012
Springer
216views Education» more  CORR 2012»
6 years 11 months ago
Fractional Moments on Bandit Problems
Reinforcement learning addresses the dilemma between exploration to find profitable actions and exploitation to act according to the best observations already made. Bandit proble...
Ananda Narayanan B., Balaraman Ravindran

1
posts
with
216
views
171profile views Browse  My Posts »
Marcin SzubertStudent, PhD
Poznan University of Technology
Marcin Szubert

Publication
240views
7 years 1 months ago
Bayesian multitask inverse reinforcement learning
We generalise the problem of inverse reinforcement learning to multiple tasks, from multiple demonstrations. Each one may represent one expert trying to solve a different task, or ...
Christos Dimitrakakis, Constantin A. Rothkopf

Publication
233views
7 years 1 months ago
Sparse reward processes
We introduce a class of learning problems where the agent is presented with a series of tasks. Intuitively, if there is relation among those tasks, then the information gained duri...
Christos Dimitrakakis
ICCCI
2011
Springer
7 years 2 months ago
Evolving Equilibrium Policies for a Multiagent Reinforcement Learning Problem with State Attractors
Multiagent reinforcement learning problems are especially difficult because of their dynamism and the size of joint state space. In this paper a new benchmark problem is proposed, ...
Florin Leon
ATAL
2011
Springer
7 years 3 months ago
Metric learning for reinforcement learning agents
A key component of any reinforcement learning algorithm is the underlying representation used by the agent. While reinforcement learning (RL) agents have typically relied on hand-...
Matthew E. Taylor, Brian Kulis, Fei Sha
GECCO
2011
Springer
276views Optimization» more  GECCO 2011»
7 years 6 months ago
Evolution of reward functions for reinforcement learning
The reward functions that drive reinforcement learning systems are generally derived directly from the descriptions of the problems that the systems are being used to solve. In so...
Scott Niekum, Lee Spector, Andrew G. Barto
books