12 search results - page 1 / 3 » Reinforcement Learning via AIXI Approximation |
104
Voted
AAAI
2010
15 years 1 months 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...
87
Voted
JAIR
2011
14 years 7 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...
130
click to vote
ATAL
2005
Springer
15 years 6 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...
91
Voted
ICML
2000
IEEE
16 years 1 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
16 years 1 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...