Learning regular sets from queries and counterexamples
Information and Computation
Diversity-based inference of finite automata
Journal of the ACM (JACM)
Sorting with fixed-length reversals
Discrete Applied Mathematics - Special volume on computational molecular biology
System identification (2nd ed.): theory for the user
System identification (2nd ed.): theory for the user
Learning algebraic structures from text
Theoretical Computer Science - Algorithmic learning theory
Observable Operator Models for Discrete Stochastic Time Series
Neural Computation
On The Complexity Of Matrix Group Problems I
SFCS '84 Proceedings of the 25th Annual Symposium onFoundations of Computer Science, 1984
Efficient structure learning in factored-state MDPs
AAAI'07 Proceedings of the 22nd national conference on Artificial intelligence - Volume 1
Finding optimal solutions to Rubik's cube using pattern databases
AAAI'97/IAAI'97 Proceedings of the fourteenth national conference on artificial intelligence and ninth conference on Innovative applications of artificial intelligence
Hierarchical heuristic search revisited
SARA'05 Proceedings of the 6th international conference on Abstraction, Reformulation and Approximation
Hi-index | 0.00 |
We investigate the problem of learning the transition dynamics of deterministic, discrete-state environments. We assume that an agent exploring such an environment is able to perform actions (from a finite set of actions) in the environment and to sense the state changes. The question investigated is whether the agent can learn the dynamics without visiting all states. Such a goal is unrealistic in general, hence we assume that the environment has structural properties an agent might exploit. In particular, we assume that the set of all action sequences forms an algebraic group. We introduce a learning model in different variants and study under which circumstances the corresponding ''group-structured environments'' can be learned efficiently by experimenting with group generators (actions). It turns out that for some classes of such environments the choice of actions given to the agent determines if efficient learning is possible. Negative results are presented, even without efficiency constraints, for rather general classes of groups, showing that even with group structure, learning an environment from partial information is far from trivial. However, positive results for special subclasses of Abelian groups turn out to be a good starting point for the design of efficient learning algorithms based on structured representations.