Markov decision processes with unknown state feature values for safe exploration using Gaussian processes
When exploring an unknown environment, a mobile robot must decide where to observe next. It must do this whilst minimising the risk of failure, by only exploring areas that it expects to be safe. In this context, safety refers to the robot remaining in regions where critical environment features (e....
Автори: | Budd, M, Lacerda, B, Duckworth, P, West, A, Lennox, B, Hawes, N |
---|---|
Формат: | Conference item |
Мова: | English |
Опубліковано: |
Institute of Electrical and Electronics Engineers
2021
|
Схожі ресурси
Схожі ресурси
-
Planning under uncertainty for safe robot exploration using Gaussian process prediction
за авторством: Stephens, A, та інші
Опубліковано: (2024) -
On solving a Stochastic Shortest-Path Markov Decision Process as probabilistic inference
за авторством: Baioumy, M, та інші
Опубліковано: (2022) -
Bayesian reinforcement learning for single-episode missions in partially unknown environments
за авторством: Budd, M, та інші
Опубліковано: (2022) -
Time-bounded mission planning in time-varying domains with semi-MDPS and Gaussian processes
за авторством: Duckworth, P, та інші
Опубліковано: (2021) -
Minimax regret optimisation for robust planning in uncertain Markov decision processes
за авторством: Rigter, M, та інші
Опубліковано: (2021)