Lucy-SKG: Learning to Play Rocket League Efficiently Using Deep Reinforcement Learning
A successful tactic that is followed by the scientific community for advancing AI is to treat games as problems, which has been proven to lead to various breakthroughs. We adapt this strategy in order to study Rocket League, a widely popular but rather under-explored 3D multiplayer video game with a distinct physics engine and complex dynamics that pose a significant challenge in developing efficient and high-performance game-playing agents. In this paper, we present Lucy-SKG, a Reinforcement Learning-based model that learned how to play Rocket League in a sample-efficient manner, outperforming by a notable margin the two highest-ranking bots in this game, namely Necto (2022 bot champion) and its successor Nexto, thus becoming a state-of-the-art agent. Our contributions include: a) the development of a reward analysis and visualization library, b) novel parameterizable reward shape functions that capture the utility of complex reward types via our proposed Kinesthetic Reward Combination (KRC) technique, and c) design of auxiliary neural architectures for training on reward prediction and state representation tasks in an on-policy fashion for enhanced efficiency in learning speed and performance. By performing thorough ablation studies for each component of Lucy-SKG, we showed their independent effectiveness in overall performance. In doing so, we demonstrate the prospects and challenges of using sample-efficient Reinforcement Learning techniques for controlling complex dynamical systems under competitive team-based multiplayer conditions.
Code (0)
등록된 구현이 없습니다.
Tasks
Deep Reinforcement Learningreinforcement-learningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
On the Verge of Solving Rocket League using Deep Reinforcement Learning and Sim-to-sim Transfer
Autonomously trained agents that are supposed to play video games reasonably well rely either on fast simulation speeds or heavy parallelization across thousands of machines running concurrently. This work explores a thi…
Deep Reinforcement LearningReinforcement Learning (RL)A Comprehensive Review of Multi-Agent Reinforcement Learning in Video Games
Recent advancements in multi-agent reinforcement learning (MARL) have demonstrated its application potential in modern games. Beginning with foundational work and progressing to landmark achievements such as AlphaStar in…
Multi-agent Reinforcement LearningStarcraft IILearning to Play Soccer by Reinforcement and Applying Sim-to-Real to Compete in the Real World
This work presents an application of Reinforcement Learning (RL) for the complete control of real soccer robots of the IEEE Very Small Size Soccer (VSSS), a traditional league in the Latin American Robotics Competition (…
Reinforcement LearningReinforcement Learning (RL)TLeague: A Framework for Competitive Self-Play based Distributed Multi-Agent Reinforcement Learning
Competitive Self-Play (CSP) based Multi-Agent Reinforcement Learning (MARL) has shown phenomenal breakthroughs recently. Strong AIs are achieved for several benchmarks, including Dota 2, Glory of Kings, Quake III, StarCr…
Dota 2Multi-agent Reinforcement Learningreinforcement-learningReinforcement Learning (RL)+2Realizing Stabilized Landing for Computation-Limited Reusable Rockets: A Quantum Reinforcement Learning Approach
The advent of reusable rockets has heralded a new era in space exploration, reducing the costs of launching satellites by a significant factor. Traditional rockets were disposable, but the design of reusable rockets for …
Computational Efficiencyreinforcement-learningReinforcement Learning