Autonomous Hierarchical POMDP Planning from Low-Level Sensors.
Shawn SquireMarie desJardinsPublished in: AAAI Workshop: Learning Rich Representations from Low-Level Sensors (2013)
Keyphrases
- low level
- belief space
- planning problems
- partially observable markov decision processes
- partially observable
- high level
- partially observable markov decision process
- higher level
- reinforcement learning
- belief state
- real time
- dynamical systems
- spatially distributed
- sensor networks
- partially observable stochastic domains
- predictive state representations
- state space
- dynamic environments
- sensor data
- planning under uncertainty
- markov decision processes
- hierarchical structure
- low level features
- sequential decision making problems
- stochastic domains
- data fusion
- visual information
- continuous state
- partial observability
- multi agent
- ai planning
- action selection
- finite state
- lower level
- cooperative
- domain independent
- markov decision process
- autonomous systems
- blocks world
- optimal policy
- visual features
- least squares
- model free reinforcement learning