Title | ||
---|---|---|
Transfer of knowledge for a climbing virtual human: a reinforcement learning approach |
Abstract | ||
---|---|---|
In the reinforcement learning literature, transfer is the capability to reuse on a new problem what has been learnt from previous experiences on similar problems. Adapting transfer properties for robotics is a useful challenge because it can reduce the time spent in the first exploration phase on a new problem. In this paper we present a transfer framework adapted to the case of a climbing Virtual Human (VH). We show that our VH learns faster to climb a wall after having learnt on a different previous wall. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/ROBOT.2009.5152553 | ICRA |
Keywords | Field | DocType |
virtual human,previous experience,useful challenge,different previous wall,adapting transfer property,transfer framework,new problem,exploration phase,similar problem,robots,foot,reinforcement learning,end effectors,humanoid robots,virtual reality,context modeling,learning artificial intelligence,computer animation,robot control,supervised learning,robotics,control systems,mechanical systems | Knowledge transfer,Supervised learning,Artificial intelligence,Engineering,Virtual actor,Robot,Climbing,Robotics,Humanoid robot,Reinforcement learning | Conference |
Volume | Issue | ISSN |
2009 | 1 | 1050-4729 |
Citations | PageRank | References |
2 | 0.40 | 11 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Benoît Libeau | 1 | 2 | 0.40 |
Alain Micaelli | 2 | 98 | 14.12 |
Olivier Sigaud | 3 | 539 | 53.35 |