mfl22

Support for ONNX export

1

Thank you for the library. Have you considered adding support for exporting factorized layers (`FactorizedConv`) to ONNX?

env() function issue

1

In the following lines: https://github.com/wsyCUHK/Reinforcement-Learning-for-Real-time-Pricing-and-Scheduling-Control-in-EV-Charging-Stations/blob/cbd4c8b3be01f779bb2c7e9fad9cc2c822b49442/code/HSA.py#L221-L223 https://github.com/wsyCUHK/Reinforcement-Learning-for-Real-time-Pricing-and-Scheduling-Control-in-EV-Charging-Stations/blob/cbd4c8b3be01f779bb2c7e9fad9cc2c822b49442/code/HSA.py#L72 https://github.com/wsyCUHK/Reinforcement-Learning-for-Real-time-Pricing-and-Scheduling-Control-in-EV-Charging-Stations/blob/cbd4c8b3be01f779bb2c7e9fad9cc2c822b49442/code/HSA.py#L28 if I am not mistaken, only the first `MAX_EP_STEP` data points are used, was that intended ?

Shouldn't parameters of local and global networks be synchronized: https://github.com/MorvanZhou/pytorch-A3C/blob/5ab27abee2c3ac3ca921ac393bfcbda4e0a91745/discrete_A3C.py#L73 `lnet` and `gnet` are not initialized with the same parameters here ? Probably `lnet.load_state_dict(gnet.state_dict())` is missing. For example, see implementation...

Supplementary Material

1

Thank you for publishing this work. You mention in the paper that more details are provided in the Supplementary. Is it available?