Implement GAE (the backward recursion) given per-token rewards and value estimates

Medium

RLHF: Reward Models, PPO & GRPO2 / 7

Chapter 122 / 7

RLHF: Reward Models, PPO & GRPO

Medium

Target interface

compute_gae(rewards, values, gamma=0.99, lam=0.95, last_value=0.0)

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 numpy as np

def compute_gae(rewards, values, gamma=0.99, lam=0.95, last_value=0.0):
    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 122 / 7

RLHF: Reward Models, PPO & GRPO

Medium

Target interface

compute_gae(rewards, values, gamma=0.99, lam=0.95, last_value=0.0)

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

Hints0 / 2

Reference solution

Your own code stays in the editor.