Made-up minds: a constructivist approach to artificial intelligence
Made-up minds: a constructivist approach to artificial intelligence
Efficient learning of typical finite automata from random walks
STOC '93 Proceedings of the twenty-fifth annual ACM symposium on Theory of computing
Diversity-based inference of finite automata
Journal of the ACM (JACM)
Discovery as Autonomous Learning from the Environment
Machine Learning
Reinforcement learning with selective perception and hidden state
Reinforcement learning with selective perception and hidden state
Blind construction of optimal nonlinear recursive predictors for discrete sequences
UAI '04 Proceedings of the 20th conference on Uncertainty in artificial intelligence
Planning in models that combine memory with predictive representations of state
AAAI'05 Proceedings of the 20th national conference on Artificial intelligence - Volume 2
Safe Q-Learning on Complete History Spaces
ECML '07 Proceedings of the 18th European conference on Machine Learning
Learning partially observable deterministic action models
Journal of Artificial Intelligence Research
Maintaining predictions over time without a model
IJCAI'09 Proceedings of the 21st international jont conference on Artifical intelligence
A Monte-Carlo AIXI approximation
Journal of Artificial Intelligence Research
PAC-Learning of markov models with hidden state
ECML'06 Proceedings of the 17th European conference on Machine Learning
Review: learning like a baby: A survey of artificial intelligence approaches
The Knowledge Engineering Review
Learning to make predictions in partially observable environments without a generative model
Journal of Artificial Intelligence Research
Recognizing internal states of other agents to anticipate and coordinate interactions
EUMAS'11 Proceedings of the 9th European conference on Multi-Agent Systems
Picking up the pieces: Causal states in noisy data, and how to recover them
Pattern Recognition Letters
Hi-index | 0.00 |
We present a solution for inferring hidden state from sensorimotor experience when the environment takes the form of a POMDP with deterministic transition and observation functions. Such environments can appear to be arbitrarily complex and non-deterministic on the surface, but are actually deterministic with respect to the unobserved underlying state. We show that there always exists a finite history-based representation that fully captures the unobserved world state, allowing for perfect prediction of action effects. This representation takes the form of a looping prediction suffix tree (PST). We derive a sound and complete algorithm for learning a looping PST from a sufficient sample of sensorimotor experience. We also give empirical illustrations of the advantages conferred by this approach, and characterize the approximations to the looping PST that are made by existing algorithms such as Variable Length Markov Models, Utile Suffix Memory and Causal State Splitting Reconstruction.