#### Filter Results:

- Full text PDF available (1)

#### Publication Year

1999

2001

- This year (0)
- Last 5 years (0)
- Last 10 years (0)

#### Publication Type

#### Journals and Conferences

#### Key Phrases

Learn More

- Vladislav Tadic
- Machine Learning
- 2001

The asymptotic properties of temporal-difference learning algorithms with linear function approximation are analyzed in this paper. The analysis is carried out in the context of the approximation of a discounted cost-to-go function associated with an uncontrolled Markov chain with an uncountable finite-dimensional state-space. Under mild conditions, the… (More)

- Vladislav Tadic
- EuroCOLT
- 1999

The mean-square asymptotic behavior of constant stepsize temporal-difference algorithms is analyzed in this paper. The analysis is carried out for the case of a linear (cost-to-go) function approximation and for the case of Markov chains with an uncountable state space. An asymptotic upper bound for the mean-square deviation of the algorithm iterations from… (More)

- Vladislav Tadic
- COLT
- 1999

The asymptotic properties of temporal-difference learning algorithms with linear function approximation are analyzed in this paper. The analysis is carried out in the context of the approximation of a discounted cost-to-go function associated to an uncontrolled Markov chain with an uncountable finite-dimensional state-space. Under very mild conditions, the… (More)

- ‹
- 1
- ›