BrightMoonStar
BrightMoonStar
Could you please introduce how to use the kitchen env and how to use the dataset https://github.com/google-research/relay-policy-learning/blob/master/kitchen_demos_multitask.zip in this project? Thank you very much!
I found that the GPU utilization when running `python simpl_meta_train.py` is very low. Could you let me know why set `trainer.policy.to('cpu')` in cpu mode here? Can we set to `GPU`...
I encountered the same problem, can you help check it, thank you! @Jdvakil @vikashplus @vmoens @ShahRutav
> 你好@BrightMoonStar，@raymondyu5和@Cranial-XIX 您能否使用 ER 算法对以下观察进行评论。 “代码在 num_worker=0 的情况下有效，但是对于不同的算法，在第一个 epoch 之后损失变为负值。因此，成功且 AoC 为 0。” 感谢您的回复。 I meet the same problem
> 你好@BrightMoonStar，@raymondyu5和@Cranial-XIX 您能否使用 ER 算法对以下观察进行评论。 “代码在 num_worker=0 的情况下有效，但是对于不同的算法，在第一个 epoch 之后损失变为负值。因此，成功且 AoC 为 0。” 感谢您的回复。 Have you solved it？Thanks for your reply!
I encountered the same problem. All the evaluation indicators were 0, including AOC, Success Rate ...
What confuses me is that the following two projects based on LIBERO also have success rate = 0 and Aoc = 0. No matter how we train, the result is...
> 经过 20 个时期的训练后，成功率将大于 0。经过 50 个时期的训练后，平均成功率约为 0.7。（对于`libero_object`任务） Have you ever tried libero-90? For libero-90, it seems the problem still exists for me. Thank you very much!