c-swm
c-swm copied to clipboard
tkipf
Contrastive Learning of Structured World Models
When I try to run the code provided here, I end up hitting a RuntimeError here: https://github.com/tkipf/c-swm/blob/e944b24bcaa42d9ee847f30163437a50f0237aa0/train.py#L104 when running your Shapes-2D build/train functions: `python train.py --dataset data/shapes_train.h5 --encoder small --name...
Hi, Kipf~I really appreciate your work. I am wondering if the GNN is modeling interactions between objects. After heading over the codes, I found that when collision happens from object...
You need to copy the following lines from `data_gen/env.py` into `data_gen/physics.py`: ``` # Get env directory import sys from pathlib import Path if str(Path.cwd()) not in sys.path: sys.path.insert(0, str(Path.cwd())) ```
Hello Kipf, I find there is a discrepancy between the loss mentioned in the paper. According to Eq(5) in paper, for negative samples, you calculate the Euclidean distance between negative...
Do you all use unique code for baseline implementations of World Models (with AE and VAE) or do you use a publicly accessible library? Can you point me toward the...
Hello, thank you for sharing the codes. I really like the Figures 3 and 4 in your paper, and wonder if there is any scripts for reproducing these results. Thanks!
Learn object representations and their relationship is intersting, but it is hard to understand how can you know all objcets at the begining for all examples.
According to the paper, the negative component of the contrastive loss is the difference between the negative states (randomly sampled from embedding at timestamp t, (z_{t}~)) and the ground truth...
max_episode_steps raises if info is None [1]. skimage import fix. [1] https://github.com/openai/gym/blob/master/gym/wrappers/time_limit.py#L19
How do you determine the corresponding state representation of the manipulated object so that you can enter the unique thermal action code into GNN along with the abstract state of...
