Sciweavers


Publication
160views
10 years 10 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
10 years 10 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
INFOCOM
2012
IEEE
12 years 5 months ago
Expected loss bounds for authentication in constrained channels
We derive bounds on the expected loss for authentication protocols in channels which are constrained due to noisy conditions and communication costs. This is motivated by a numbe...
Christos Dimitrakakis, Aikaterini Mitrokotsa, Serg...

Publication
240views
12 years 5 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
151views
12 years 5 months ago
Robust Bayesian reinforcement learning through tight lower bounds
In the Bayesian approach to sequential decision making, exact calculation of the (subjective) utility is intractable. This extends to most special cases of interest, such as reinfo...
Christos Dimitrakakis