Giters
ikostrikov
/
implicit_q_learning
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
216
Watchers:
5
Issues:
9
Forks:
35
ikostrikov/implicit_q_learning Issues
Code for Behavior cloning policy
Updated
9 months ago
Why use a positive learning rate in finetuning?
Updated
a year ago
The log_prob is not corrected
Closed
a year ago
Comments count
1
missing dextrous env
Updated
2 years ago
A question about the toy umaze environment in Figure 2?
Closed
2 years ago
Comments count
2
A small problem
Closed
2 years ago
A question about the `sample_actions()`
Closed
2 years ago
Comments count
3
Potential issue in scaling rewards in train_finetune.py.
Closed
3 years ago
Comments count
2
conflicting dependencies between optax and jaxlib
Closed
3 years ago
Comments count
6