通过模仿学习学习玩超级粉碎兄弟近战的人工智能
An AI that learns to play Super Smash Bros. Melee via imitation learning (2024-02-22, Python, 0KB, 下载0次)
使多模态模型能够在计算机上玩游戏的框架。
A framework to enable multi-modal models to play games on a computer. (2024-02-18, Python, 0KB, 下载0次)
零玩家版本的社交演绎游戏，狼人。现在是人工智能。
Zero-player version of the social deduction game, Werewolf. Now with AI. (2024-01-27, Python, 0KB, 下载0次)
ChatGPT试图玩1978年版本的俄勒冈小径。，
ChatGPT attempts to play through the 1978 version of The Oregon Trail., (2023-08-25, Python, 0KB, 下载0次)
一个人工智能，将使用您的网络摄像头对您玩石头剪刀。，
An AI that will play rock-paper-scissors against you, using your webcam., (2020-10-21, Python, 0KB, 下载0次)
人工智能检测你的手及其手势，并与你玩石头剪刀，
AI detects your hand and its gesture and plays rock paper scissors with you, (2022-02-06, Python, 0KB, 下载0次)
一个可以在隔离游戏中击败人类玩家的人工智能代理，
An AI agent that can beat human players in the game of Isolation, (2017-06-21, Python, 0KB, 下载0次)
训练人工智能代理与DQN.玩松鸡。，
Training AI agent to play flappy bird with DQN., (2023-04-18, Python, 0KB, 下载0次)
玩棋盘游戏Isolation的AI代理。（使用极大极小和α-β修剪。），
AI agent that plays the board game Isolation. (Using minimax and alpha- beta pruning.), (2017-08-18, Python, 0KB, 下载0次)
在玩Google Brain的十亿单词语言模型时使用的各种脚本，
Various scripts used while playing around with Google Brain s billion word language model, (2016-10-10, Python, 0KB, 下载0次)
使用AlphaGo-Zero算法，强化学习代理学习玩连接4
Using the AlphaGo Zero algorithm, a reinforcement learning agent learns to play conncet 4 (2020-09-29, Python, 0KB, 下载0次)
AlphaGo Zero玩3d连接四游戏的方法
AlphaGo Zero approach to playing 3d connect-four game (2020-03-08, Python, 0KB, 下载0次)
一个玩狼人的框架&为狼人开发和测试人工智能代理。
A framework for playing Werewolf & developing and testing AI agents for Werewolf. (2021-05-23, Python, 2929KB, 下载0次)
各种小型人工智能项目的集合，通常是那些玩游戏的项目。
A collection of various small AI projects, generally those that play games. (2021-04-13, Python, 6155KB, 下载0次)
将sc2环境转换为健身房atari并玩一些迷你游戏
Convert sc2 environment to gym-atari and play some mini-games (2017-10-28, Python, 5KB, 下载0次)
玩cartpole游戏的DQN模型和Actor-Critric模型
A DQN model and an Actor-Critic model to play cartpole game (2018-03-20, Python, 5KB, 下载0次)
POODLE的正式实施：通过惩罚分发外的样本来改进少试学习（NeurIPS 2021）
Official implementation of POODLE: Improving Few-shot Learning via Penalizing Out-of-Distribution Samples (NeurIPS 2021) (2022-08-06, Python, 883KB, 下载0次)
小行星IA，使用遗传算法和人工神经网络训练人工智能玩小行星
AsteroidsIA,Training a AI to play Asteroids using Genetic Algorithm and Artificial Neural Network (2020-11-04, Python, 336989KB, 下载0次)
WZCQ,用基于策略梯度得强化学习方法训练AI玩王者荣耀
WZCQ, Training AI King of Glory with Strategy Gradient Based Reinforcement Learning Method (2021-11-16, Python, 39KB, 下载0次)
PlaneDQN,通过深度强化学习训练的AI玩起游戏来也是有板有眼,将人类玩家远远甩在身后。本文就将为您介绍如何训练AI玩微信飞机大战,biubiubiu~
PlaneDQN, an AI trained through deep reinforcement learning, plays games with a disciplined approach, leaving human players far behind. This article will introduce how to train AI to play WeChat airplane battles, biubiubiu~ (2019-02-14, Python, 13073KB, 下载0次)