Goal Recognition over POMDPs: Inferring the Intention of a POMDP Agent.
Miquel RamírezHector GeffnerPublished in: IJCAI (2011)
Keyphrases
- partially observable markov decision process
- belief state
- partially observable
- partially observable markov decision processes
- multi agent
- decision theoretic
- reinforcement learning
- dec pomdps
- state space
- partially observable markov decision
- belief space
- partial observations
- single agent
- markov decision processes
- finite state
- recognition rate
- continuous state
- object recognition
- markov decision process
- point based value iteration
- partial observability
- dynamical systems
- planning under uncertainty
- multi agent systems
- infinite horizon
- decision problems
- multiple agents
- optimal policy
- dynamic programming
- intelligent agents
- multiagent systems
- stochastic domains
- markov decision problems
- reward function
- belief revision
- agent model
- expected reward
- model free reinforcement learning
- partially observable stochastic games
- planning problems
- hidden state
- policy gradient
- decision making
- autonomous agents
- decision theoretic planning
- action space
- planning domains
- approximate solutions
- sequential decision making problems