Links on all articles mentioned during the lecture could be found in "References" at the very end of the presentation slides. All other interesing links which contribute to the topic of POMDP are presented below
- Our lecture and seminar
- A lecture on basics by Andrew NG (english, LQ) - video
- our lectures are underway...
- A lecture on lecture by 5vision (russian) - video
- [alternative] Chalkboard-style 2-part lecture by B. Ravindran. - part1, part2
- [alternative] Yet another mini-lecture touching on POMDP by S.S. Baveja - video
- DRQN lecture by Fritz448 (russian) - video
- Data efficient learning in continous POMDP
- Managing wind farms with bayesian POMDP
- Bayesian learning and decision-making in dynamic environments
- Introduction to planning in POMDP, ch.: 6
- Bayes filters in robotics, ch.: 3, 4
- SOTA in scalable approximate offline planning: SARSOP and PLEASE which is build on top of the former
- SOTA in scalable approximate online planning: DESPOT
- Not SOTA but very useful and enlightening online planning approach: POMCP
- Realizations of SARSOP, DESPOT and MCVI in C++
- Recent approaches combining POMDP planning with learning on top of neural networks: Predictron, historgram filter and QMDP-Net
We have a detailed description of the entire lab in the homework notebook
Homework is platform and framewerk independent, so choose the ones which suit you best, but pay attention on how many you will need to implement youself in case of nonstandart ones.