Abstract | ||
---|---|---|
In this paper we improve learning performance of a risk-aware robot facing navigation tasks by employing transfer learning; that is, we use information from a previously solved task to accelerate learning in a new task. To do so, we transfer risk-aware memoryless stochastic abstract policies into a new task. We show how to incorporate risk-awareness into robotic navigation tasks, in particular when tasks are modeled as stochastic shortest path problems. We then show how to use a modified policy iteration algorithm, called AbsProb-PI, to obtain risk-neutral and risk-prone memoryless stochastic abstract policies. Finally, we propose a method that combines abstract policies, and show how to use the combined policy in a new navigation task. Experiments validate our proposals and show that one can find effective abstract policies that can improve robot behavior in navigation problems. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1007/978-3-662-44468-9_23 | ROBOCUP 2013: ROBOT WORLD CUP XVII |
Keywords | Field | DocType |
Risk-Awareness, Memoryless Stochastic Abstract Policies, Transfer Learning | Computer vision,Shortest path problem,Reuse,Simulation,Computer science,Transfer of learning,Artificial intelligence,Behavior-based robotics,Robot,Machine learning | Conference |
Volume | ISSN | Citations |
8371 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 14 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Valdinei Freire da Silva | 1 | 25 | 6.86 |
Marcelo Li Koga | 2 | 3 | 0.77 |
Fábio Cozman | 3 | 18 | 10.16 |
Anna Helena Reali Costa | 4 | 192 | 31.97 |