Abstract | ||
---|---|---|
In this paper, we propose a variant of the dynamic programming which is suitable for solving infinite Markov decision processes on GPUs. The primary feature of the proposed method is to not always but intermittently transfer and check values for proving the convergence of the procedure. It is expected for the proposed method to decrease computational times by suppressing surplus transfers and checks of values. This expectation is verified through applications of some dynamic programming programs to a simple animat problem and the mountain-car problem. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/CANDAR.2013.44 | CANDAR |
Keywords | Field | DocType |
simple animat problem,dynamic programming program,intermittently transfer,infinite markov decision process,mountain-car problem,suppressing surplus transfer,primary feature,computational time,intermittently proving dynamic programming,dynamic programming,solve infinite mdps,markov processes | Convergence (routing),Dynamic programming,Mathematical optimization,Markov process,Computer science,Parallel computing,Inductive programming,Markov decision process,Animat,Reactive programming,General-purpose computing on graphics processing units | Conference |
Citations | PageRank | References |
0 | 0.34 | 2 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tsutomu Inamoto | 1 | 0 | 2.37 |
Yoshinobu Higami | 2 | 140 | 27.24 |
Shin-ya Kobayashi | 3 | 38 | 8.60 |