Reinforcement Learning Algorithms for Regret Minimization in Structured Markov Decision Processes: (Extended Abstract).
Prabuchandran K. J.Tejas BodasTheja TulabandhulaPublished in: AAMAS (2016)
Keyphrases
- extended abstract
- reinforcement learning algorithms
- markov decision processes
- regret minimization
- state space
- reinforcement learning
- markov games
- dynamic programming
- game theoretic
- optimal policy
- finite state
- nash equilibrium
- policy iteration
- reward function
- partially observable
- markov decision process
- decision processes
- infinite horizon
- action space
- average reward
- temporal difference
- total reward
- control problems
- multiagent reinforcement learning
- stochastic games
- partially observable markov decision processes
- decision problems
- average cost
- cost function
- game theory