aaaccc444的博客

Unity-ML-Agents--The behavior name 3DBall01 has not been specified in the trainer configuration.

Unity-ML-Agents--The type or namespace name 'MLAgents' does not exist in the namespace 'Unity' (are you missing an assembly reference?)

论文解析-基于 Unity3D 游戏人工智能的研究与应用1.重写AgentAction 方法2.重写CollectObservations 方法3.重写CollectObservations 方法

1.Profiling in Python1.1@timed装饰器1.2hierarchical_timer上下文管理器1.3Adding Profiling1.4Parallel execution

可以在c#和Python中创建自己的侧通道，并使用它在两者之间通信自定义数据结构。为了使用侧通道，必须将其实现为Unity和Python类。1.Unity C# 示例1.1StringLogSideChannel类1.2RegisterStringLogSideChannel类2. Python示例2.1StringLogChannel类2.2ML-Agents Python 与 Unity Editor 通信

Unity-ML-Agents-Food Collector环境-FoodCollectorSettings.cs1.FoodCollectorSettings.cs1.1FoodCollectorSettings类1.2 Awake()函数1.3EnvironmentReset()1.4ClearObjects()1.5 Update()

Unity-ML-Agents-Sampler.cs

Unity-ML-Agents注意事项及报错、警告等解决方式1.注意事项2.警告和报错

Unity-ML-Agents-Soccer Twos环境(3)-AgentSoccer.cs1. AgentSoccer.cs1.1 导入命名空间1.2AgentSoccer类1.3Initialize()1.4 MoveAgent()函数1.5OnActionReceived()1.6Heuristic()方法1.7OnCollisionEnter()1.8OnEpisodeBegin()

Unity-ML-Agents-Soccer Twos环境(2)-SoccerBallController.cs1. SoccerBallController.cs1.1 导入命名空间1.2SoccerBallController类1.3 Start()方法1.4OnCollisionEnter()函数

1.SoccerEnvController.cs1.1 导入命名空间1.2SoccerEnvController 类1.3 PlayerInfo类1.4XML 注释标签1.5 定义字段1.6Start() 方法1.7FixedUpdate()方法1.8ResetBall()方法1.9GoalTouched()方法1.10ResetScene() 方法

Unity-ML-Agents-Example Learning Environments-环境解析(1)1.Push Block2.Cooperative Push Block3.Dungeon Escape4.Soccer Twos5.Worm

Unity-ML-Agents--Learning-Environment-Design-Agents.md-代码解读(2)1.Normalization2.Continuous Actions3.Discrete Actions4.Masking Discrete Actions5.Rewards6.Agent Properties7.Defining Multi-agent Scenarios

Unity-ML-Agents--Learning-Environment-Design-Agents.md-代码解读(1)1.Agent.CollectObservations()2.Observable Fields and Properties3.One-hot encoding categorical information

Unity-ML-Agents-训练生成的results文件解读-PushBlock1.push_block_test_021.1 PushBlock1.2 run_logs1.3configuration.yaml1.4PushBlock.onnx

Unity-ML-Agents-配置文件解读-PushBlock.yamllearning_rate_schedule：学习率调整策略，这里是线性调整。network_settings：神经网络设置，包括以下几个：normalize：是否对输入数据进行归一化处理hidden_units：每个隐藏层中神经元的数量num_layers：隐藏层数量vis_encode_type：可视化编码类型，这里是simplereward_signals：奖励信号设置

Unity-ML-Agents-代码解读-Making a New Learning Environment1.Initialization and Resetting the Agent2. Observing the Environment3.Taking Actions and Assigning Rewards4.问题

Unity-ML-Agents安装1.下载ML-Agents2.下载Anaconda3.虚拟环境4. 安装cuda和cudnn

Unity3D -知识点（1）场景视图认识脚本组件Script API坐标系与旋转

Unity3D- Visual Studio 2022 打开项目提示项目不兼容