12 search results - page 1 / 3 » Reinforcement Learning via AIXI Approximation |
AAAI
2010
14 years 9 days ago
2010
This paper introduces a principled approach for the design of a scalable general reinforcement learning agent. This approach is based on a direct approximation of AIXI, a Bayesian...
JAIR
2011
13 years 5 months ago
2011
This paper describes a computationally feasible approximation to the AIXI agent, a universal reinforcement learning agent for arbitrary environments. AIXI is scaled down in two ke...
ATAL
2005
Springer
14 years 4 months ago
2005
Springer
Reinforcement learning problems are commonly tackled with temporal difference methods, which use dynamic programming and statistical sampling to estimate the long-term value of ta...
ICML
2000
IEEE
14 years 11 months ago
2000
IEEE
This paper discusses theoretical and experimental aspects of gradient-based approaches to the direct optimization of policy performance in controlled ??? ?s. We introduce ??? ?, a...
ICML
2009
IEEE
14 years 11 months ago
2009
IEEE
We cast model-free reinforcement learning as the problem of maximizing the likelihood of a probabilistic mixture model via sampling, addressing both the infinite and finite horizo...