richardwth

How did you derive the gradient of GenerateProFlow?

1

Hi, thanks for the wonderful paper and code. I am trying to extend your method in my application where the project distortion is more flexible, that is, `x3 = 1...

Is env.parameters.NB_TIMESTEP_COOLDOWN_SUB 0 or 3?

3

`env.parameters.NB_TIMESTEP_COOLDOWN_SUB` is 0 in training data but 3 in starting_kit validation data. Should it be 0 or 3 in online test? ``` from grid2op import make env = make("l2rpn_wcci_2022") print(env.parameters.NB_TIMESTEP_COOLDOWN_SUB)...

actual_dispatch added to target_dispatch when the previous target_dispatch is 0 but actual_dispatch is not

1

## Environment - Grid2op version: `1.7.2` - System: `ubuntu18.04` ## Bug description When `obs.target_dispatch` is 0 and `obs.actual_dispatch` is not 0 at time `t`, the `obs.actual_dispatch` will be added to...

## Environment - Grid2op version: `1.7.2` - System: `ubuntu18.04` ## Bug description When there is no dispatch action on any generator, the `gen_max_ramp_up` constraint may be ignored. ## How to...

Output 0 of MatMul8bitLtBackward is a view and is being modified inplace.

10

I would like to report a bug using `MatMul8bitLt`. ### Bug description When I used the following three in my code: - `flash_attn_varlen_func` from flash_attn (v2.0.8, [Github Link](https://github.com/Dao-AILab/flash-attention)), - `MatMul8bit`...

Support for data with instance-wise dictionary as features

11

### Feature request I notice that when loading data instances with feature type of python dictionary, the dictionary keys would be broadcast so that every instance has the same set...