Questions on reinforcement learning for a driving policy: How do GRPO and PPO differ? When would you choose a hand-written heuristic reward over a learned reward model, and the reverse? Implement a reward that keeps the vehicle at or under the speed limit, computed over batched trajectories of shape [batch, num_waypoints, ...] .

Reinforcement learning for driving: PPO vs GRPO and a speed-limit reward

TeslaAI/ML designLast asked Feb 2026

Questions on reinforcement learning for a driving policy:

How do GRPO and PPO differ?
When would you choose a hand-written heuristic reward over a learned reward model, and the reverse?
Implement a reward that keeps the vehicle at or under the speed limit, computed over batched trajectories of shape [batch, num_waypoints, ...].

Your canvas

Draw your answer hereBoxes, arrows and notes, saved for you to come back to.Sign in to start drawing