Fever Basketball: A Complex, Flexible, and Asynchronized Sports Game Environment for Multi-agent Reinforcement Learning

• URL: http://arxiv.org/abs/2012.03204v1
• Date: Sun, 6 Dec 2020 07:51:59 GMT
• Title: Fever Basketball: A Complex, Flexible, and Asynchronized Sports Game Environment for Multi-agent Reinforcement Learning
• Authors: Hangtian Jia, Yujing Hu, Yingfeng Chen, Chunxu Ren, Tangjie Lv, Changjie Fan, Chongjie Zhang
• Abstract summary: We introduce the Fever Basketball game, a novel reinforcement learning environment where agents are trained to play basketball game. It is a complex and challenging environment that supports multiple characters, multiple positions, and both the single-agent and multi-agent player control modes. To better simulate real-world basketball games, the execution time of actions differs among players, which makes Fever Basketball a novel asynchronized environment.
• Score: 38.4742699455284
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The development of deep reinforcement learning (DRL) has benefited from the emergency of a variety type of game environments where new challenging problems are proposed and new algorithms can be tested safely and quickly, such as Board games, RTS, FPS, and MOBA games. However, many existing environments lack complexity and flexibility and assume the actions are synchronously executed in multi-agent settings, which become less valuable. We introduce the Fever Basketball game, a novel reinforcement learning environment where agents are trained to play basketball game. It is a complex and challenging environment that supports multiple characters, multiple positions, and both the single-agent and multi-agent player control modes. In addition, to better simulate real-world basketball games, the execution time of actions differs among players, which makes Fever Basketball a novel asynchronized environment. We evaluate commonly used multi-agent algorithms of both independent learners and joint-action learners in three game scenarios with varying difficulties, and heuristically propose two baseline methods to diminish the extra non-stationarity brought by asynchronism in Fever Basketball Benchmarks. Besides, we propose an integrated curricula training (ICT) framework to better handle Fever Basketball problems, which includes several game-rule based cascading curricula learners and a coordination curricula switcher focusing on enhancing coordination within the team. The results show that the game remains challenging and can be used as a benchmark environment for studies like long-time horizon, sparse rewards, credit assignment, and non-stationarity, etc. in multi-agent settings.

Related papers

• SkillMimic: Learning Reusable Basketball Skills from Demonstrations [85.23012579911378]
  We propose SkillMimic, a data-driven approach that mimics both human and ball motions to learn a wide variety of basketball skills. SkillMimic employs a unified configuration to learn diverse skills from human-ball motion datasets. The skills acquired by SkillMimic can be easily reused by a high-level controller to accomplish complex basketball tasks.
  arXiv  Detail & Related papers  (2024-08-12T15:19:04Z)
• Basketball-SORT: An Association Method for Complex Multi-object Occlusion Problems in Basketball Multi-object Tracking [1.7331775755285384]
  We propose an online and robust MOT approach, named Basketball-SORT, which focuses on the CMOO problems in basketball videos. Our method achieves a Higher Order Tracking Accuracy (HOTA) score of 63.48$%$ on the basketball fixed video dataset.
  arXiv  Detail & Related papers  (2024-06-28T04:49:57Z)
• FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning [25.857375787748715]
  We present FightLadder, a real-time fighting game platform, to empower competitive MARL research. We provide implementations of state-of-the-art MARL algorithms for competitive games, as well as a set of evaluation metrics. We demonstrate the feasibility of this platform by training a general agent that consistently defeats 12 built-in characters in single-player mode.
  arXiv  Detail & Related papers  (2024-06-04T08:04:23Z)
• A Black-box Approach for Non-stationary Multi-agent Reinforcement Learning [53.83345471268163]
  We investigate learning the equilibria in non-stationary multi-agent systems. We show how to test for various types of equilibria by a black-box reduction to single-agent learning.
  arXiv  Detail & Related papers  (2023-06-12T23:48:24Z)
• Centralized control for multi-agent RL in a complex Real-Time-Strategy game [0.0]
  Multi-agent Reinforcement learning (MARL) studies the behaviour of multiple learning agents that coexist in a shared environment. MARL is more challenging than single-agent RL because it involves more complex learning dynamics. This project provides the end-to-end experience of applying RL in the Lux AI v2 Kaggle competition.
  arXiv  Detail & Related papers  (2023-04-25T17:19:05Z)
• TiZero: Mastering Multi-Agent Football with Curriculum Learning and Self-Play [19.98100026335148]
  TiZero is a self-evolving, multi-agent system that learns from scratch. It outperforms previous systems by a large margin on the Google Research Football environment.
  arXiv  Detail & Related papers  (2023-02-15T08:19:18Z)
• On the Convergence of No-Regret Learning Dynamics in Time-Varying Games [89.96815099996132]
  We characterize the convergence of optimistic gradient descent (OGD) in time-varying games. Our framework yields sharp convergence bounds for the equilibrium gap of OGD in zero-sum games. We also provide new insights on dynamic regret guarantees in static games.
  arXiv  Detail & Related papers  (2023-01-26T17:25:45Z)
• Off-Beat Multi-Agent Reinforcement Learning [62.833358249873704]
  We investigate model-free multi-agent reinforcement learning (MARL) in environments where off-beat actions are prevalent. We propose a novel episodic memory, LeGEM, for model-free MARL algorithms. We evaluate LeGEM on various multi-agent scenarios with off-beat actions, including Stag-Hunter Game, Quarry Game, Afforestation Game, and StarCraft II micromanagement tasks.
  arXiv  Detail & Related papers  (2022-05-27T02:21:04Z)
• Generating Diverse and Competitive Play-Styles for Strategy Games [58.896302717975445]
  We propose Portfolio Monte Carlo Tree Search with Progressive Unpruning for playing a turn-based strategy game (Tribes) We show how it can be parameterized so a quality-diversity algorithm (MAP-Elites) is used to achieve different play-styles while keeping a competitive level of play. Our results show that this algorithm is capable of achieving these goals even for an extensive collection of game levels beyond those used for training.
  arXiv  Detail & Related papers  (2021-04-17T20:33:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.