Keyphrases
- partially observable markov decision processes
- reinforcement learning
- vision system
- object manipulation
- belief state
- point based value iteration
- distributed constraint optimization
- partially observable
- markov decision processes
- finite state
- policy search
- continuous state
- predictive state representations
- planning under uncertainty
- manipulation tasks
- machine learning
- neural network
- decision problems
- state space
- database
- robot control
- computer vision
- dec pomdps
- data sets