PAC Reinforcement Learning with Rich Observations.
Akshay KrishnamurthyAlekh AgarwalJohn LangfordPublished in: NIPS (2016)
Keyphrases
- reinforcement learning
- state space
- function approximation
- learning algorithm
- high level
- reinforcement learning algorithms
- markov decision processes
- model free
- dynamic programming
- upper bound
- real world
- noise tolerant
- sample complexity
- optimal control
- optimal policy
- neural network
- learning problems
- support vector
- multi agent
- function approximators
- transition model