# Axioms for Rational Reinforcement Learning

@inproceedings{Sunehag2011AxiomsFR, title={Axioms for Rational Reinforcement Learning}, author={Peter Sunehag and Marcus Hutter}, booktitle={ALT}, year={2011} }

We provide a formal, simple and intuitive theory of rational decision making including sequential decisions that affect the environment. The theory has a geometric flavor, which makes the arguments easy to visualize and understand. Our theory is for complete decision makers, which means that they have a complete set of preferences. Our main result shows that a complete rational decision maker implicitly has a probabilistic model of the environment. We have a countable version of this result… CONTINUE READING

#### Topics from this paper.

8 Citations

Rationality, optimism and guarantees in general reinforcement learning

- Computer Science, Mathematics
- 2015

11

#### References

##### Publications referenced by this paper.

SHOWING 1-10 OF 22 REFERENCES