Implement DAPO on a toy RLVR task: clip-higher, dynamic sampling (drop all-correct/all-wro

Super-hard

RLHF: Reward Models, PPO & GRPO7 / 7

Chapter 127 / 7

RLHF: Reward Models, PPO & GRPO

Implement DAPO on a toy RLVR task: clip-higher, dynamic sampling (drop all-correct/all-wro

Super-hard

Implement DAPO on a toy RLVR task: clip-higher, dynamic sampling (drop all-correct/all-wrong groups), token-level loss, and overlong reward shaping. [NVIDIA]

Target interface

overlong_shaping(reward, length, soft_cap, hard_cap, penalty=1.0)

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

def overlong_shaping(reward, length, soft_cap, hard_cap, penalty=1.0):
    raise NotImplementedError

def dapo_loss(logp_new, logp_old, rewards, lengths, mask, G, eps_low=0.2, eps_high=0.28, soft_cap=4, hard_cap=8):
    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 127 / 7

RLHF: Reward Models, PPO & GRPO

Implement DAPO on a toy RLVR task: clip-higher, dynamic sampling (drop all-correct/all-wro

Super-hard

Implement DAPO on a toy RLVR task: clip-higher, dynamic sampling (drop all-correct/all-wrong groups), token-level loss, and overlong reward shaping. [NVIDIA]

Target interface

overlong_shaping(reward, length, soft_cap, hard_cap, penalty=1.0)

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

Hints0 / 2

Reference solution

Your own code stays in the editor.