Universal Reinforcement Learning Algorithms: Survey and Experiments.
John AslanidesJan LeikeMarcus HutterPublished in: IJCAI (2017)
Keyphrases
- reinforcement learning algorithms
- reinforcement learning
- state space
- model free
- markov decision processes
- temporal difference
- reinforcement learning problems
- learning algorithm
- eligibility traces
- function approximation
- reward function
- reinforcement learning methods
- partially observable environments
- function approximators
- optimal policy
- training set
- policy search