Extending Environments to Measure Self-reflection in Reinforcement Learning.
Samuel Allen AlexanderMichael CastanedaKevin CompherOscar MartinezPublished in: J. Artif. Gen. Intell. (2022)
Keyphrases
- reinforcement learning
- state space
- function approximation
- reinforcement learning algorithms
- learning algorithm
- dynamic environments
- real world
- multi agent environments
- highly dynamic
- autonomous robots
- supervised learning
- dynamic programming
- learning process
- similarity measure
- information retrieval
- machine learning
- data sets
- distance measure
- image quality
- multi agent
- learning problems
- correlation coefficient
- information content
- website
- model free
- multi agent reinforcement learning