Bias Mitigation via Compensation: A Reinforcement Learning Perspective.
Nandhini SwaminathanDavid DanksPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- function approximation
- state space
- dynamic programming
- temporal difference
- markov decision processes
- viewpoint
- reinforcement learning algorithms
- image sequences
- model free
- learning algorithm
- machine learning
- multi agent reinforcement learning
- learning process
- learning problems
- control problems
- robot control
- learning tasks
- optimal policy
- database
- trade off
- multi agent systems
- multi agent
- artificial intelligence
- real world
- neural network
- data sets