Pruning the Way to Reliable Policies: A Multi-Objective Deep Q-Learning Approach to Critical Care.
Ali ShiraliAlexander SchubertAhmed AlaaPublished in: CoRR (2023)
Keyphrases
- multi objective
- critical care
- optimal policy
- evolutionary algorithm
- reinforcement learning
- medical staff
- state space
- objective function
- reward function
- genetic algorithm
- medical care
- markov decision processes
- information seeking
- ecg signals
- learning algorithm
- search space
- statistical analysis
- data warehouse
- air traffic control
- dynamic programming