Is Deep Reinforcement Learning Really Superhuman on Atari?
Marin ToromanoffÉmilie WirbelFabien MoutardePublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- linear value function approximation
- function approximation
- reinforcement learning algorithms
- model free
- optimal policy
- state space
- markov decision processes
- optimal control
- neural network
- learning process
- action selection
- control problems
- reinforcement learning problems
- markov games
- learning algorithm
- temporal difference
- multi agent
- single agent
- markov decision problems