Universal Reinforcement Learning Algorithms: Survey and Experiments.
John AslanidesJan LeikeMarcus HutterPublished in: CoRR (2017)
Keyphrases
- reinforcement learning algorithms
- reinforcement learning
- state space
- model free
- markov decision processes
- reinforcement learning problems
- eligibility traces
- reinforcement learning methods
- function approximation
- temporal difference
- partially observable environments
- learning algorithm
- stochastic games
- reward function
- policy search
- function approximators
- dynamic environments
- step size
- policy gradient
- hidden markov models
- neural network