Visual Rationalizations in Deep Reinforcement Learning for Atari Games.
Laurens WeitkampElise van der PolZeynep AkataPublished in: BNCAI (2018)
Keyphrases
- reinforcement learning
- linear value function approximation
- function approximation
- state space
- learning algorithm
- temporal difference learning
- control problems
- temporal difference
- model free
- reinforcement learning algorithms
- markov decision processes
- game theory
- reinforcement learning methods
- game theoretic
- neural network
- optimal policy
- supervised learning
- dynamic programming
- multi agent
- machine learning