Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Self-Optimizing and Pareto-Optimal Policies in General Environments Based on Bayes-Mixtures
COLT '02 Proceedings of the 15th Annual Conference on Computational Learning Theory
The Speed Prior: A New Simplicity Measure Yielding Near-Optimal Computable Predictions
COLT '02 Proceedings of the 15th Annual Conference on Computational Learning Theory
Artificial Intelligence: A Modern Approach
Artificial Intelligence: A Modern Approach
Universal Artificial Intelligence: Sequential Decisions Based On Algorithmic Probability
Universal Artificial Intelligence: Sequential Decisions Based On Algorithmic Probability
An Introduction to Kolmogorov Complexity and Its Applications
An Introduction to Kolmogorov Complexity and Its Applications
Self-modification and mortality in artificial agents
AGI'11 Proceedings of the 4th international conference on Artificial general intelligence
Delusion, survival, and intelligent agents
AGI'11 Proceedings of the 4th international conference on Artificial general intelligence
Universal knowledge-seeking agents
ALT'11 Proceedings of the 22nd international conference on Algorithmic learning theory
ALT'11 Proceedings of the 22nd international conference on Algorithmic learning theory
Asymptotic non-learnability of universal agents with computable horizon functions
Theoretical Computer Science
Optimistic agents are asymptotically optimal
AI'12 Proceedings of the 25th Australasian joint conference on Advances in Artificial Intelligence
Memory issues of intelligent agents
AGI'12 Proceedings of the 5th international conference on Artificial General Intelligence
AGI'12 Proceedings of the 5th international conference on Artificial General Intelligence
Universal knowledge-seeking agents
Theoretical Computer Science
| Hi-index | 0.00 |
Finding the universal artificial intelligent agent is the old dream of AI scientists. Solomonoff Induction was one big step towards this, giving a universal solution to the general problem of Sequence Prediction, by defining a universal prior distribution. Hutter defined AIXI which extends the latter to the Reinforcement Learning framework, where almost all if not all AI problems can be formulated. However, new difficulties arise, because the agent is now active, whereas it is only passive in the Sequence Prediction case. This makes proving AIXI's optimality difficult. In fact, we prove that the current definition of AIXI can sometimes be only suboptimal in a certain sense, and we generalize this result to infinite horizon agents and to any static prior distribution.