Research engineering training discussionML designDiscuss training approaches for long-context and long-horizon tasks, then explore past projects, environment design and reward design with team leads. Reported on 1point3acres'…
Last asked Sep 2026
#reinforcement learning
Design an LLM chatbot with RL-trained answersAI system designDesign a chatbot that answers users' questions in real time, built on a large language model. Cover the serving path (latency, streaming answers, scale), then the learning loop:…Last asked Sep 2026
Pipeline parallelism in GRPO trainingML designExplain pipeline parallelism and how it applies when a language model is trained with GRPO: how the model is split into stages across devices, how micro-batches keep the stages…Last asked Aug 2026- Importance sampling in LLM trainingML designExplain importance sampling: what it is and why it works. Then explain where it is used when training large language models and why it is used there. Expect to go beyond the…Last asked Aug 2026
- Detect and prevent reward hackingML designExplain reward hacking when a language model is trained with reinforcement learning: what it looks like, how you would detect it, and what you would change in the reward, the data…Last asked Aug 2026
Debug a GRPO training script and defend the RL mathML designBelow is a small group relative policy optimization (GRPO) trainer in plain Python. The policy is a table of logits per prompt, and the reward is the share of tokens that match…Last asked Mar 2026
Reinforcement learning for driving: PPO vs GRPO and a speed-limit rewardML designQuestions on reinforcement learning for a driving policy: 1. How do GRPO and PPO differ? 2. When would you choose a hand-written heuristic reward over a learned reward model, and…Last asked Feb 2026
GRPO in NumPy: group-relative advantages, process and shaped rewardsML designIn a notebook, implement the core math of Group Relative Policy Optimization with NumPy. For each prompt the policy samples a group of completions, each completion gets a score…Last asked Jan 2026- GRPO-style reinforcement learning for diffusion modelsML designExplain how a group-relative policy optimisation method (GRPO) works for language models, then how you would adapt it to fine-tune a diffusion model against a reward: what counts…Last asked Dec 2025
- Design an asynchronous RL post-training systemML designDesign a system for post-training a large language model with reinforcement learning where generation (rollouts) and training run asynchronously. Cover how rollout workers and…Last asked Sep 2025