Tackling Decision Processes with Non-Cumulative Objectives using Reinforcement Learning.
Maximilian NägeleJan OlleThomas FöselRemmy ZenFlorian MarquardtPublished in: CoRR (2024)
Keyphrases
- decision processes
- reinforcement learning
- markov decision processes
- decision problems
- decision process
- state space
- decision making
- optimal policy
- function approximation
- reasoning process
- finite state
- partially observable
- learning algorithm
- infinite horizon
- dynamic programming
- decision support system
- partially observable markov decision processes
- model free
- optimal control
- reward function
- multi agent
- machine learning
- np hard