这是一个A2C代理使用稳定的baselines3库玩PandaReachDense-v3的训练模型。
This is a trained model of a A2C agent playing PandaReachDense-v3 using the stable-baselines3 library. (2024-04-28, Others, 0KB, 下载0次)
AI代理学习和玩不同游戏的平台,实时展示他们的能力。
A platform for AI agents to learn and play different games, showcasing their abilities in real-time. (2024-03-11, Others, 0KB, 下载0次)
Andrew Ng在Coursera上为斯坦福大学学习机器学习专业化课程时保存的应用程序项目文件
My Saved application Project files while taking Machine Learning Specialization Course for Stanford University by Andrew Ng on Coursera (2024-02-29, Others, 0KB, 下载0次)
通过实现Minimax算法为人类玩家提供人工智能对手。
AI opponent for a human player by implementing the Minimax algorithm. (2024-02-16, Others, 0KB, 下载0次)
将玩游戏的神经网络。学习遗传算法的知识库
Neural networks that will play the game. Repository to learn genetic algorithm (2024-01-24, Others, 0KB, 下载0次)
这是一个神经网络,可以根据你的动作学习玩Tic Tac Toe。
It’s a Neural Network that learns to play Tic Tac Toe based on your moves. (2024-01-18, Others, 0KB, 下载0次)
一种翼展人工智能,使用强化学习来学习玩翼展棋盘游戏。
A Wingspan AI that uses reinforcement learning to learn to play the wingspan board game. (2024-01-04, Others, 0KB, 下载0次)
人工智能使用增强拓扑NEAT的神经进化来学习玩Flappybird
An AI learns to play Flappybird using Neural Evolution with Augmenting Topology NEAT (2023-12-23, Others, 0KB, 下载0次)
使用强化学习玩几何短跑游戏的人工智能模型
An AI model that uses reinforcement learning to play Geometry Dash game (2023-12-18, Others, 0KB, 下载0次)
这个游戏很有趣,你可以和你的朋友一起玩
This game is very fun and you can play with your friends (2023-12-10, Others, 0KB, 下载0次)
Java中的国际象棋引擎-可能实现AI来学习如何玩,
Chess Engine in Java - possibly implement AI to learn how to play, (2023-10-16, Others, 0KB, 下载0次)
使用强化Q学习训练用于玩模拟游戏(神奇宝贝黄色)的神经网络。,
A neural network trained to play emulated games (Pokemon Yellow) using reinforcement Q learning., (2023-09-29, Others, 0KB, 下载0次)
在斯坦福大型电影评论数据集上训练RNN。它涉及使用单词嵌入和双向LSTM层。退学的是我们...,
Trained an RNN on the Stanford Large Movie Review Dataset. It involved using Word Embeddings and Bidirectional LSTM layers. Dropout is used to tackle overfitting, resulting in a final accuracy of 87%. (2023-09-10, Others, 0KB, 下载0次)
使用遗传算法训练人工智能玩Flappy bird,
Training AI to play Flappy bird using genetic algorithm, (2023-08-05, Others, 0KB, 下载0次)
基于资源组合的机器学习课程(斯坦福的cs221n,伊恩·古德费罗的深度学习书,普林斯顿COS495,G...,
Machine Learning course built on a combination of resources (Stanford s cs221n, Iain Goodfellow s Deep Learning Book, Princeton COS495, Gilbert Strang s MIT18.06, NASA FDL, Fast.AI, NVIDIA resources & others) (2019-03-20, Others, 0KB, 下载0次)
毕达哥拉斯是一个遵循LLaMA模型的指令,根据斯坦福大学哲学百科全书所有条目的文本和数字进行了微调...,
Pythagoras is an instruction-following LLaMA model fine-tuned on text and figures from all Stanford Encyclopedia of Philosophy entries and linked pages. (2023-03-22, Others, 0KB, 下载0次)
来自斯坦福大学、麻省理工学院、加州大学伯克利分校等顶尖大学的AI_Curriculum、开放式深度学习和强化学习讲座。
AI_Curriculum,Open Deep Learning and Reinforcement Learning lectures from top Universities like Stanford, MIT, UC Berkeley. (2021-04-02, Others, 5336KB, 下载0次)
chinese-book,《深度学习:一起玩转TensorLayer》资源分享、讨论
Chinese book, "Deep Learning: Playing TensorLayer Together" resource sharing and discussion (2018-02-22, Others, 1912KB, 下载0次)
用基本C++语言实现的解决运筹学对偶问题的程序,需要提交对偶问题程序的朋友可以一试
A program implemented in Basic C Language to solve the dual problem of operations research can be tried by a friend who needs to submit the program of dual problem. (2018-09-05, Others, 7KB, 下载0次)
机器学习算法实现使用octave语言,初级简单练习,斯坦福大学在线课程
Machine learning algorithm using octave language, primary simple exercise, Stanford university online courses
(2012-03-09, Others, 12KB, 下载20次)