Closed hjh0119 closed 1 month ago
Thank you for your review and questions. Below are the answers to your queries:
The python-sc2 library provides a foundational codebase along with several examples that assisted in building this framework. Thus, Text-sc2 can be considered an extended version of python-sc2. I also received guidance from Burnysc2, the author of python-sc2, who possesses extensive knowledge in this area.
The Observation-to-Text Adapter converts game metadata into macro information typically used by both language models and humans.
The Text-to-Action Adapter similarly transforms these language descriptions into specific game actions.
O2T Process: GameData -> metadata -> language information StarCraft2 -> python-sc2 -> TextSC2
T2A Process: Language description -> python script -> game operation TextSC2 -> python-sc2 -> StarCraft2
As mentioned in our paper, during the Human vs. LLM Agent tests, we utilized a finetuned model similar to models like qwen2-7b and other open-source LLMs, and we have also released these datasets and models. Thus, the human tests were conducted under real-time conditions.
Thank you for your detailed response
Awesome work!
I have reviewed the paper and have several questions that I hope can be addressed.
What is the difference between textsc2 and python-sc2? The paper mentions the
Observation-to-Text Adapter
and theText-to-Action Adapter
, but there is no detailed explanation provided.What is the difference between a real-time agent and a non-real-time agent? I reviewed the code, and it seems that the distinction lies in whether the real-time agent constructs an L2 prompt. If this is the case, does the paper's claim that the LLM agent can achieve the skill level of a gold-ranked human player refer to the real-time agent?
Following up on the second point, are the experimental results in the paper based on the non-real-time agent?