ML-Agents2

• 

  [ML-Agents] 3D Ball 실습 22.07.11 Unity ML PPO (Proximal Policy Optimization) SAC (Soft Actor-Critic) Curiosity MA-POCA (MultiAgent POsthumous Credit Assignment) 3D Ball 예제 C:\ml-agents-main\ml-agents-main\config\ppo 3DBall.yaml behaviors: 3DBall: trainer_type: ppo hyperparameters: batch_size: 64 buffer_size: 12000 learning_rate: 0.0003 // beta: 0.001 epsilon: 0.2 lambd: 0.99 num_epoch: 3 learning_rate_schedule: linear .. 🎮Unity 2022. 8. 8.

• 

  [ML-Agents] ML-Agents 톺아보기 22.07.08 Machine Learning 기계가 학습을 할 수 있도록 함 Artificial Intelligence Machine Learning Deep Learning Machine Learning 지도 학습 준지도 학습 비지도 학습 강화 학습 Reinforcement Learning Data → Learning → Program → solving → output ML-agent *2.0 / 1.0 Python과 Unity 환경 간 통신 🎮Unity 2022. 8. 8.