Stochastic systems: estimation, identification and adaptive control
Stochastic systems: estimation, identification and adaptive control
Artificial intelligence: a modern approach
Artificial intelligence: a modern approach
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
Optimality of universal Bayesian sequence prediction for general loss and alphabet
The Journal of Machine Learning Research
Universal Artificial Intelligence: Sequential Decisions Based On Algorithmic Probability
Universal Artificial Intelligence: Sequential Decisions Based On Algorithmic Probability
Prediction, Learning, and Games
Prediction, Learning, and Games
Reinforcement learning in POMDPs without resets
IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
General discounting versus average reward
ALT'06 Proceedings of the 17th international conference on Algorithmic Learning Theory
Defensive universal learning with experts
ALT'05 Proceedings of the 16th international conference on Algorithmic Learning Theory
On Finding Predictors for Arbitrary Families of Processes
The Journal of Machine Learning Research
Characterizing predictable classes of processes
UAI '09 Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence
Optimistic agents are asymptotically optimal
AI'12 Proceedings of the 25th Australasian joint conference on Advances in Artificial Intelligence
Hi-index | 5.23 |
We address the problem of reinforcement learning in which observations may exhibit an arbitrary form of stochastic dependence on past observations and actions, i.e. environments more general than (PO)MDPs. The task for an agent is to attain the best possible asymptotic reward where the true generating environment is unknown, but belongs to a known countable family of environments. We find some sufficient conditions on the class of environments under which an agent exists which attains the best asymptotic reward for any environment in the class. We analyze how tight these conditions are, and how they relate to different probabilistic assumptions known in reinforcement learning and related fields, such as Markov Decision Processes and mixing conditions.