|
|||||
|
|
An actor-critic algorithm for constrained Markov decision processes |
|
| Authors: | VS Borkar |
| Affiliation: | School of Technology and Computer Science, Tata Institute of Fundamental Research, Homi Bhabha Road, Mumbai 400005, India |
| Abstract: | An actor-critic type reinforcement learning algorithm is proposed and analyzed for constrained controlled Markov decision processes. The analysis uses multiscale stochastic approximation theory and the envelope theorem' of mathematical economics. |
| Keywords: | Actor-critic algorithms Reinforcement learning Constrained Markov decision processes Stochastic approximation Envelope theorem |
| 本文献已被 ScienceDirect 等数据库收录！ | |