Reinforcement Learning Algorithms for Uncertain, Dynamic, Zero-Sum Games.
Snehasis MukhopadhyayOmkar J. TilakSubir ChakrabartiPublished in: ICMLA (2018)
Keyphrases
- reinforcement learning algorithms
- reinforcement learning
- dynamic environments
- model free
- markov decision processes
- state space
- reinforcement learning problems
- decision making
- learning algorithm
- function approximation
- temporal difference
- eligibility traces
- training data
- reinforcement learning methods
- policy search
- neural network
- partially observable environments