-
The loss used for calculating the gradient to perform the meta update is only from one task. However, it should be the sum of all sampled tasks according to the original paper. Please look at step 8 i…
-
Hi, I've been trying to replicate some of your results and compare against Reptile, for the reinforcement learning case. Specifically, I'm trying to run the point mass experiments.
After installing…
-
Hi！
An error occurs when I run MAML.py. Can you give me some advice? Thanks a lot!
**Issue summary**
Traceback (most recent call last):
File "MAML.py", line 149, in
v_loss, v_ppl = do_ev…
-
Is there something wrong with the production of training data? It seems that the size of each trajectory in the data is not the same, so in training, the iterative data cannot be stack properly. The f…
-
```
Traceback (most recent call last):
File "train_maml_system.py", line 14, in
maml_system = ExperimentBuilder(model=model, data=data, args=args, device=device)
File "/workspace/assign_3…
-
### What happened + What you expected to happen
MBMPO fails to reproduce. Below I show an error using Pendulum task config from https://github.com/ray-project/ray/blob/master/rllib/tuned_examples/m…
-
https://github.com/rcmalli/lightning-maml/blob/ce7eedc8a5b23ac89fd95113dd96d50f6feda165/src/pl/model.py#L140
According to context, it seems to be test_logit instead of train_logit.
-
Did you use method like MAML to train the model? If not, where is the meta part?
-
In contrastive_learning_based_MAML.py, meta_update_model() takes 4 positional arguments but 5 were given, how to update model and head?
-
Hi, I noticed that when using `torch.autograd.grad`, the implementation does not pass `create_graph` parameter which by default is `False`. See [L#86](https://github.com/dragen1860/MAML-Pytorch/blob/m…