Explainability in reinforcement learning: perspective and position.
Agneza KrajnaMario BrcicTomislav LipicJuraj DoncevicPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- function approximation
- robotic control
- markov decision processes
- temporal difference
- multi agent
- stochastic approximation
- state space
- position and orientation
- viewpoint
- control problems
- real world
- optimal policy
- direct policy search
- position information
- reinforcement learning algorithms
- relative position
- dynamic environments
- learning process
- artificial neural networks
- learning environment
- website
- learning algorithm