#### Filter Results:

- Full text PDF available (15)

#### Publication Year

2006

2018

- This year (5)
- Last 5 years (11)
- Last 10 years (14)

#### Publication Type

#### Co-author

#### Journals and Conferences

Learn More

- Felipe W. Trevizan, Manuela M. Veloso
- Artif. Intell.
- 2014

Stochastic Shortest Path Problems (SSPs) are a common representation for probabilistic planning problems. Two approaches can be used to solve SSPs: (i) consider all probabilistically reachable statesâ€¦ (More)

- Felipe W. Trevizan, Manuela M. Veloso
- ICAPS
- 2012

Algorithms to solve probabilistic planning problems can be classified in probabilistic planners and replanners. Probabilistic planners invest significant computational effort to generate a closedâ€¦ (More)

We consider the problem of generating optimal stochastic policies for Constrained Stochastic Shortest Path problems, which are a natural model for planning under uncertainty for resource-boundedâ€¦ (More)

One of the machine learning challenges posed by the robot soccer domain is to learn the opponents strategies. A team that may be able to do it efficiently may have the advantage to adapt its ownâ€¦ (More)

- Felipe W. Trevizan, Leliane Nunes de Barros, FlÃ¡vio S. CorrÃªa da Silva
- Inteligencia Artificial, Revista Iberoamericanaâ€¦
- 2006

- Felipe W. Trevizan, Manuela M. Veloso
- NIPS
- 2012

Probabilistic planning captures the uncertainty of plan execution by probabilistically modeling the effects of actions in the environment, and therefore the probability of reaching different statesâ€¦ (More)

- Felipe W. Trevizan, Sylvie ThiÃ©baux, Patrik Haslum
- ICAPS
- 2017

For the past 25 years, heuristic search has been used to solve domain-independent probabilistic planning problems, but with heuristics that determinise the problem and ignore precious probabilisticâ€¦ (More)

- Sam Toyer, Felipe W. Trevizan, Sylvie ThiÃ©baux, Lexing Xie
- AAAI
- 2018

In this paper, we introduce the Action Schema Network (ASNet): a neural network architecture for learning generalised policies for probabilistic planning problems. By mimicking the relationalâ€¦ (More)

Many planning problems require maximizing the probability of goal satisfaction as well as minimizing the expected cost to reach the goal. To model and solve such problems, there have been severalâ€¦ (More)

- Felipe M. Santos, Leliane N. Barros, Felipe W. Trevizan
- Journal of the Brazilian Computer Society
- 2015

This paper presents how to improve model reduction for Markov decision process (MDP), a technique that generates equivalent MDPs that can be smaller than the original MDP. In order to improve theâ€¦ (More)