Metrics for Assessing Generalization of Deep Reinforcement Learning in Parameterized Environments.
Maciej AleksandrowiczJoanna Jaworek-KorjakowskaPublished in: J. Artif. Intell. Soft Comput. Res. (2023)
Keyphrases
- reinforcement learning
- markov decision processes
- multi agent environments
- reinforcement learning algorithms
- learning algorithm
- function approximation
- evaluation metrics
- dynamic environments
- optimal policy
- machine learning
- dynamic programming
- multi agent
- database
- autonomous robots
- learning machines
- highly dynamic
- genetic algorithm
- temporal difference learning
- multi agent reinforcement learning