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....
Những tác giả chính: | Budd, M, Lacerda, B, Duckworth, P, West, A, Lennox, B, Hawes, N |
---|---|
Định dạng: | Conference item |
Ngôn ngữ: | English |
Được phát hành: |
Institute of Electrical and Electronics Engineers
2021
|
Những quyển sách tương tự
-
Planning under uncertainty for safe robot exploration using Gaussian process prediction
Bằng: Stephens, A, et al.
Được phát hành: (2024) -
On solving a Stochastic Shortest-Path Markov Decision Process as probabilistic inference
Bằng: Baioumy, M, et al.
Được phát hành: (2022) -
Bayesian reinforcement learning for single-episode missions in partially unknown environments
Bằng: Budd, M, et al.
Được phát hành: (2022) -
Time-bounded mission planning in time-varying domains with semi-MDPS and Gaussian processes
Bằng: Duckworth, P, et al.
Được phát hành: (2021) -
Minimax regret optimisation for robust planning in uncertain Markov decision processes
Bằng: Rigter, M, et al.
Được phát hành: (2021)