Visualization of Deep Reinforcement Learning using Grad-CAM: How AI Plays Atari Games?
Ho-Taek JooKyung-Joong KimPublished in: CoG (2019)
Keyphrases
- reinforcement learning
- linear value function approximation
- reinforcement learning algorithms
- machine learning
- function approximation
- game theory
- reinforcement learning problems
- nash equilibria
- video games
- model free
- temporal difference learning
- computer games
- markov decision problems
- control problems
- state space
- optimal control
- temporal difference
- game playing
- nash equilibrium
- markov decision processes
- optimal policy
- game play
- markov games
- stochastic games
- markov decision process
- game tree
- game theoretic
- transfer learning
- cooperative
- multi agent
- learning algorithm