Implement the Bradley–Terry pairwise reward-model loss in PyTorch

Easy

RLHF: Reward Models, PPO & GRPO1 / 7

Chapter 121 / 7

RLHF: Reward Models, PPO & GRPO

Implement the Bradley–Terry pairwise reward-model loss in PyTorch

Easy

Target interface

bt_loss(reward_chosen: torch.Tensor, reward_rejected: torch.Tensor)

Complete the starter code in the editor. Any correct approach is accepted.

Hints0 / 2

Reference solution

Your own code stays in the editor.

solution.pyPython

Local draft

import torch
import torch.nn.functional as F

def bt_loss(reward_chosen: torch.Tensor, reward_rejected: torch.Tensor) -> torch.Tensor:
    raise NotImplementedError

Local draft

⌘/Ctrl↵to submit

AI review

Ready when you are

Submit your solution for a score and feedback on correctness, edge cases, and clarity. Any correct approach is accepted.

Chapter 121 / 7

RLHF: Reward Models, PPO & GRPO

Implement the Bradley–Terry pairwise reward-model loss in PyTorch

Easy

Target interface

bt_loss(reward_chosen: torch.Tensor, reward_rejected: torch.Tensor)

Complete the starter code in the editor. Any correct approach is accepted.

Hints0 / 2

Reference solution

Your own code stays in the editor.