ABSTRACT
1. INTRODUCTION
2. LITERATURE REVIEW
3. TASKS AND REWARDS IN AM-MARL
3.1 Task Definition
3.2 Reward Functions
3.3 Learning Algorithms
3.4 Evaluation Setups
4. METHODOLOGY AND EXPERIMENTAL RESULTS
4.1 Multi-Agent Environment and Task Design
4.2 Reward Modeling and Rationale
4.3 Learning Algorithms
4.4 Experimental Design and Configurations
4.5 Results and Interpretation
DISCUSSION
CONCLUSION AND FUTURE WORKS
ACKNOWLEDGEMENTS
REFERENCES