A Competition Winning Deep Reinforcement Learning Agent in microRTS

2024-02-12 · Scott Goodfriend

Scripted agents have predominantly won the five previous iterations of the IEEE microRTS ($\mu$RTS) competitions hosted at CIG and CoG. Despite Deep Reinforcement Learning (DRL) algorithms making significant strides in real-time strategy (RTS) games, their adoption in this primarily academic competition has been limited due to the considerable training resources required and the complexity inherent in creating and debugging such agents. RAISocketAI is the first DRL agent to win the IEEE microRTS competition. In a benchmark without performance constraints, RAISocketAI regularly defeated the two prior competition winners. This first competition-winning DRL submission can be a benchmark for future microRTS competitions and a starting point for future DRL research. Iteratively fine-tuning the base policy and transfer learning to specific maps were critical to RAISocketAI's winning performance. These strategies can be used to economically train future DRL agents. Further work in Imitation Learning using Behavior Cloning and fine-tuning these models with DRL has proven promising as an efficient way to bootstrap models with demonstrated, competitive behaviors.

📄 PDF Abstract BibTeX arXiv:2402.08112

Code (1)

sgoodfriend/rl-algo-impls 공식 구현 jax

Tasks

Deep Reinforcement LearningImitation Learningreinforcement-learning Reinforcement Learning Transfer Learning

Methods 이 논문이 사용한 방법론

BASE 설명 없음

microPhantom: Playing microRTS under uncertainty and chaos

2020-05-22 · Florian Richoux

This competition paper presents microPhantom, a bot playing microRTS and participating in the 2020 microRTS AI competition. microPhantom is based on our previous bot POAdaptive which won the partially observable track of…

Decision Making Decision Making Under Uncertainty

Gym-$μ$RTS: Toward Affordable Full Game Real-time Strategy Games Research with Deep Reinforcement Learning

2021-05-21 · Shengyi Huang, Santiago Ontañón, Chris Bamford, Lukasz Grela

In recent years, researchers have achieved great success in applying Deep Reinforcement Learning (DRL) algorithms to Real-time Strategy (RTS) games, creating strong autonomous agents that could defeat professional player…

Deep Reinforcement Learning GPU Real-Time Strategy Games reinforcement-learning+4

RangL: A Reinforcement Learning Competition Platform

2022-07-28 · Viktor Zobernig, Richard A. Saldanha, Jinke He, Erica van der Sar 외

The RangL project hosted by The Alan Turing Institute aims to encourage the wider uptake of reinforcement learning by supporting competitions relating to real-world dynamic decision problems. This article describes the r…

OpenAI Gym reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Choosing Well Your Opponents: How to Guide the Synthesis of Programmatic Strategies

2023-07-10 · Rubens O. Moraes, David S. Aleixo, Lucas N. Ferreira, Levi H. S. Lelis

This paper introduces Local Learner (2L), an algorithm for providing a set of reference strategies to guide the search for programmatic strategies in two-player zero-sum games. Previous learning algorithms, such as Itera…

Tactical Reward Shaping: Bypassing Reinforcement Learning with Strategy-Based Goals

2019-10-08 · Yizheng Zhang, Andre Rosendo

Deep Reinforcement Learning (DRL) has shown its promising capabilities to learn optimal policies directly from trial and error. However, learning can be hindered if the goal of the learning, defined by the reward functio…

Deep Reinforcement Learning Q-Learning reinforcement-learning Reinforcement Learning+1