Visual Explanation using Attention Mechanism in Actor-Critic-based Deep Reinforcement Learning.
Hidenori ItayaTsubasa HirakawaTakayoshi YamashitaHironobu FujiyoshiKomei SugiuraPublished in: IJCNN (2021)
Keyphrases
- actor critic
- reinforcement learning
- attention mechanism
- temporal difference
- policy gradient
- approximate dynamic programming
- optimal control
- reinforcement learning algorithms
- function approximation
- neuro fuzzy
- gradient method
- policy iteration
- state space
- machine learning
- visual features
- policy gradient methods
- visual attention
- average reward
- dynamic programming
- low level
- multi agent
- linear program
- markov decision processes
- dynamical systems
- monte carlo
- evaluation function
- learning problems
- transfer learning
- markov decision process
- image quality
- higher order
- real time