Explainable Deep Reinforcement Learning Using Introspection in a Non-episodic Task.
Angel AyalaFrancisco CruzBruno J. T. FernandesRichard DazeleyPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- function approximation
- learning algorithm
- optimal policy
- state space
- function approximators
- reinforcement learning algorithms
- temporal difference
- multi agent
- machine learning
- temporal difference learning
- transfer learning
- deep learning
- learning process
- dynamic programming
- multi agent reinforcement learning
- model free
- social networks
- robotic control
- partially observable
- dynamical systems
- control system
- website
- knowledge base
- genetic algorithm