Chengcheng Han
Chengcheng Han
🎶🎶🎶🫰
Hi~ gitizens, Thank you for using FRIDAY~ Currently, FRIDAY only supports single-turn conversations, and all API tools need to be configured before use. If you need to view the list...
We have updated the code, and the structure of the code released this time is clearer and more convenient to use. Please try it again, and if you have any...
We are considering integrating more open-source models into OS-Copilot, and Ollama is a great tool that can help us achieve this goal quickly. Thank you for your suggestion~
Sorry, currently FRIDAY only supports mac and Linux systems.
def pg_error(data: namedtuple) -> namedtuple: """ **概述**: 策略梯度（Policy Gradient，PG）算法的 PyTorch 实现。 """ # 对数据 data 进行解包: $$$$ logit, action, return_ = data # 根据 logit 构建策略分布，然后得到对应动作的概率的对数值。 dist = torch.distributions.categorical.Categorical(logits=logit) log_prob...