-
-
🐛 Bug Bounty: Fix Needed! 🛠️
Reward: :trophy: 500 USDC 🏆
We are excited to announce a bug bounty for third-party developers! If you've got the skills and know-how, here's your chance to earn so…
-
Hello, I am a student who is just beginning to learn RL, I have run the examples of VALOR code.
I have a question about the reward, which is gotten from the extrinsic environment. I think the rewa…
-
![image](https://github.com/user-attachments/assets/f408c593-01e7-40eb-b406-85aef946c8d1)
# Determines if the player loses required items when completing a GET quest.
take_items_for_get_quests: tr…
-
I found a bug in the reward function in the file "./env/starcraft2/starcraft2.py", line 729. The bug is that when the enemies heal or regenerate shield, the allies will receive rewards. The location o…
-
-
[X] `ToDo`: Add function to finish post and distribute the reward.
[X] `ToDo`: Add reward distribution feature
-
### Feature request
The RewardTrainer has a default behavior of printing four chosen & rejected responses along with their logits at every validation iteration. This is implemented in the following l…
-
**Modpack Version:**
0.5.1
**Describe the bug**
The reward for finishing the challenge bonus for Meet the Udders seem to be missing. The rewards should be from the mods curios and bountifulbauble…
-
Hello, I’ve been following your work recently. Based on the configurations in your repo, it seems that the reward queries for REBEL are twice as for DDPO, since REBEL uses two sampling traces per batc…