heyzude

ardrone.move3D(vx, vy, vz, vr): Doesn't go forward when giving valid vx value!

4

Hi, thanks for giving your great code ^^. But I have a problem. Although I gave valid vx or vy value, my drone hardly goes forward or backward, left or...

Please wrap `delta_r_warmup` at line 202 of darc.agent.py with `int()`: `int(delta_r_warmup)`.

When following Magenta's Score2perf's README, checkpoint doesn't have some keys

2

Ubuntu 18.04 Python 3.7.9 Tensorflow 2.3.1 When I follow https://github.com/magenta/magenta/blob/master/magenta/models/score2perf/README.md, The problem happens when I follow **Training** and **Sampling from the model** part. The Training command is like below at...

When I try to restore weights from checkpoint, following Score2perf's README, checkpoint doesn't have some keys

5

Ubuntu 18.04 Python 3.7.9 Tensorflow 2.3.1 When I follow https://github.com/magenta/magenta/blob/master/magenta/models/score2perf/README.md, checkpoint doesn't have some keys The problem happens when I follow **Training** and **Sampling from the model** part. This issue...

Hi, thank you for opensourcing your work! I have a question about pretraining phase. I'm about to test Duet on R2R, but I wonder when you got the R2R performance...

It seems that there is a +/- sign typo

1

In `vpg_multi_stein.py`, at line 212, I guess it should be `weights = (1.0 / self.temp) * kernel[:, :, None] * gradient[:, None, :] - kernel_gradient[:, :, :]`, not `weights =...

Are the positions of subgoals(in craft for example, iron, grass, wood, gold, ...) Fixed?

1

May I ask Are the positions of subgoals fixed in all experiment environments, at multitask and zero-shot settings? At first after reading the paper only, I thought that subpolicy pi...

Thanks for sharing your wonderful work! I wonder about the few-shot learning setting of ATTEMPT. Did you run a limited number of gradient descent for each datapoint (e.g. 10 GD...

Hi, and thanks for sharing your great work! I have a question. The key intuition behind C-RLFT in the implementation perspective is to apply Return-weighted behavior cloning and goal-conditioned RL...