Nonzero-Sum Risk-Sensitive Stochastic Games on a Countable State Space.
Arnab BasuMrinal K. GhoshPublished in: Math. Oper. Res. (2018)
Keyphrases
- risk sensitive
- stochastic games
- markov decision processes
- state space
- average cost
- markov chain
- reinforcement learning algorithms
- optimal policy
- average reward
- dynamic programming
- finite state
- reinforcement learning
- infinite horizon
- heuristic search
- model free
- policy iteration
- finite horizon
- state variables
- action space
- dynamical systems
- objective function
- partially observable
- markov decision process
- markov decision problems
- initial state
- optimal control
- search space
- reward function
- planning problems
- belief state
- state transition
- transition probabilities
- random walk
- learning agent
- decision problems
- search algorithm