Generality detection of hierarchical PPO based on animal cognition experimental environment
• Use Tensorflow to build a hierarchical PPO neural network (Proximal Policy Optimization) for Reinforcement learning, which is used to train the agent in the environment based on animal cognition experiments I set up on Unity3D
•Test whether the trained model has the ability to deal with the cognitive experiment environment that it has never encountered before, so as to understand the generality of this neural network architecture.