Review for NeurIPS paper: Towards Playing Full MOBA Games with Deep Reinforcement Learning

Additional Feedback: some details: p1 - define MOBA in the abstract - such as multi-agent, grammar - attention already reference(s)? Why is this no longer computationally feasible exactly? - Note that there still lacks a ... grammar - [Our] AI [system] achieved ... - How many players is the "top 0.04%"? The paper requires a thourough proofreading effort to make it publishable in the NeuRIPS proceedings. How important is this incorporated expert knowledge? "s.t." is commonly used as definition or optimization constraint.