Task-guided IRL in POMDPs that scales.
Franck DjeumouChristian EllisMurat CubuktepeCraig LennonUfuk TopcuPublished in: Artif. Intell. (2023)
Keyphrases
- reinforcement learning
- inverse reinforcement learning
- belief state
- multiple scales
- partially observable markov decision processes
- learning algorithm
- belief space
- partially observable
- markov decision processes
- dynamic programming
- search algorithm
- neural network
- finite state
- edge detection
- multi agent
- multiscale
- markov decision problems
- bayesian networks
- distributed constraint optimization