POLY-HOOT: Monte-CarloPlanninginContinuous SpaceMDPswithNon-AsymptoticAnalysis
–Neural Information Processing Systems
Inthis paper, we consider Monte-Carlo planning in an environment with continuous state-action spaces, amuchlessunderstood problem withimportant applications in control and robotics.
Neural Information Processing Systems
Feb-8-2026, 00:03:03 GMT
- Country:
- Technology: