Julien Roy

TypeError: unsupported operand type(s) for <<

1

When I run game.py with either `arthur` or `random_agent`, I get the following error : ``` Traceback (most recent call last): File "game.py", line 237, in status = main() File...

Cannot exactly reproduce results from "Quick Example"

10

Hi, First thanks for this contribution, it is sure useful to have a tool to easily compute CCM in python! I am unable to reproduce with exactitude your demonstration from...

Fixes a few bugs when using Envelope Q-learning probably introduced gradually over time (we don't run it very often).

Adding SC-Scorer

1

Adding SCScorer in gflownet/models. This might be a more interesting metric / reward to use for synthetic accessibility than SA-score, see: https://pubs.acs.org/doi/abs/10.1021/acs.jcim.7b00622. (not for immediate use but I had been...

Experiments using a ReplayBuffer have lead to surprising results where the model would be incapable to learn if our list of `flat_rewards` (tensors of shape (2,) ) would be stacked...

`cvxopt` currently is tricky to install on M1 chip laptops: > ERROR: Failed building wheel for cvxopt [More info here](https://github.com/cvxpy/cvxpy/issues/1190). Make sure to [revert this back](https://github.com/recursionpharma/gflownet/blob/b3c1238d5d6175cc81fc2e9010242d712d0b0be5/src/gflownet/utils/metrics.py#L153-L156) to top-level import of...