Value Iteration in Continuous Actions, States and Time.
Michael LutterShie MannorJan PetersDieter FoxAnimesh GargPublished in: CoRR (2021)
Keyphrases
- action space
- state space
- initial state
- markov decision processes
- state transitions
- state action
- perceptual aliasing
- belief state
- continuous action
- action sequences
- partially observable markov decision processes
- goal state
- markov decision process
- partially observable
- partial knowledge
- reinforcement learning
- dynamic programming
- decision theoretic
- belief space
- plan recognition
- state variables
- markov decision problems
- state information
- state transition
- optimal policy
- data sets
- piecewise linear
- mobile robot
- reasoning about actions
- internal states
- heuristic search
- human activities
- human actions
- situation calculus
- search space
- markov decision chains