AI4Finance-Foundation / ElegantRL

Massively Parallel Deep Reinforcement Learning. 🔥
https://ai4finance.org
Other
3.62k stars 833 forks source link

A2C算法训练无法收敛,AgentDiscreteA2C未实现完成 #306

Open ljn114514 opened 1 year ago

ljn114514 commented 1 year ago

您好,我直接使用demo_A2C_PPO.py训练pendulum环境下的A2C算法无法收敛,可能算法实现上有问题。AgentDiscreteA2C算法仅继承了AgentDiscretePPO,并未实现自己的update_net函数

Yonv1943 commented 1 year ago

谢谢,我今天检查一下