Reinforcement Learning algorithms for regret minimization in structured Markov Decision Processes.
Prabuchandran K. J.Tejas BodasTheja TulabandhulaPublished in: CoRR (2016)
Keyphrases
- reinforcement learning algorithms
- markov decision processes
- regret minimization
- reinforcement learning
- state space
- finite state
- optimal policy
- nash equilibrium
- markov games
- dynamic programming
- reward function
- policy iteration
- game theoretic
- partially observable
- stochastic games
- average cost
- markov decision process
- infinite horizon
- action space
- model free
- partially observable markov decision processes
- game theory
- decision processes
- transfer learning
- multiagent reinforcement learning
- cost function
- search algorithm