Safe Policies for Factored Partially Observable Stochastic Games.
Steven CarrNils JansenSudarshanan BharadwajMatthijs T. J. SpaanUfuk TopcuPublished in: Robotics: Science and Systems (2021)
Keyphrases
- partially observable stochastic games
- partially observable markov decision processes
- state space
- dynamic programming
- optimal policy
- multi agent
- finite state
- reinforcement learning
- decision problems
- dynamical systems
- nash equilibrium
- markov decision processes
- belief state
- long run
- orders of magnitude
- learning algorithm
- probability distribution
- bayesian networks
- decision making