Keyphrases
- planning problems
- partially observable markov decision processes
- partially observable
- belief space
- online learning
- state space
- reinforcement learning
- partially observable stochastic domains
- real time
- partially observable markov decision process
- dynamical systems
- heuristic search
- decision theoretic
- planning domains
- belief state
- plan generation
- planning under uncertainty
- planning process
- multi agent
- point based value iteration
- predictive state representations
- hidden markov models
- continuous state
- least squares
- decision problems
- ai planning
- finite state