Task-Guided IRL in POMDPs that Scales.
Franck DjeumouChristian EllisMurat CubuktepeCraig LennonUfuk TopcuPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- belief state
- partially observable markov decision processes
- inverse reinforcement learning
- partially observable environments
- optimal policy
- markov decision processes
- reward function
- multiple scales
- partially observable
- point based value iteration
- machine learning
- distributed constraint optimization
- continuous state
- multi agent
- multiscale
- genetic algorithm