Summary of A Competition Winning Deep Reinforcement Learning Agent in Microrts, by Scott Goodfriend
A Competition Winning Deep Reinforcement Learning Agent in microRTS
by Scott Goodfriend
First submitted to arxiv on: 12 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper presents a significant breakthrough in the field of Real-Time Strategy (RTS) games, where a Deep Reinforcement Learning (DRL) agent, RAISocketAI, wins the IEEE microRTS competition for the first time. This achievement is remarkable, considering that previous winners were scripted agents. The DRL algorithm was trained without performance constraints and consistently defeated prior champions in benchmark tests. The winning strategy involves iteratively fine-tuning the base policy and transferring learning to specific maps. These approaches can be used to economically train future DRL agents. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary In simple terms, a team of researchers created an AI agent that can play a popular computer game better than previous winners. This is special because those winners were already great at playing the game, but this new AI can learn and improve on its own. The researchers used a type of machine learning called Deep Reinforcement Learning to create the winning AI. They made it work by letting it practice and adjust to different situations in the game. |
Keywords
* Artificial intelligence * Fine tuning * Machine learning * Reinforcement learning
