Results for “learning-rate-scheduling”

Design a spaced retrieval schedule for any topic list and timeline. Use when planning units, term sequences, or revision programmes.

Wrap a learning session in a plan → monitor → reflect cycle. Use at the start of any substantial study session to set goals, mid-session to check strategy, and at session end to consolidate what changed. Builds self-regulated learning as a habit.

Turn model work into a production ML system with data contracts, reproducible training, quality gates, deployable artifacts, and monitoring.

Build a learning progression showing prerequisite-to-mastery steps for a target skill or understanding. Use when sequencing content, designing diagnostics, or mapping prerequisite gaps.

Fine-tune and align language models using reinforcement learning with TRL, including SFT, DPO, PPO, GRPO, and reward model training.

Design a structured goal-setting protocol using SMART or implementation-intention frameworks for students. Use when launching units, projects, or developing student self-direction habits.

Turns model work into a production ML system with data contracts, reproducible training, quality gates, deployable artifacts, and monitoring.

Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.

Run Karpathy-style autonomous ML search on a real training repo: choose the right mode (setup, program.md, bounded loop, results interpretation, or constrained-hardware adaptation), preserve the immutable prepare.py / 300-second / val_bpb contract, and route prompt/skill eval work away to LangSmith, Promptfoo, Braintrust, or skill-autoresearch.

Designing and evaluating AI/ML systems: prompt engineering, RAG design, LLM application patterns, AI safety, evaluation frameworks, MLOps, cost optimization. Use for AI pipelines or eval harnesses.

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training

针对 Modular RAG MCP Server 项目的老师式复习 Agent。按章节带领用户系统复习项目知识点，每道题互动问答、给出参考答案，复习结束后记录掌握进度，每次开始时回顾上次进度并建议继续或复习。Use when user says '复习项目', '帮我复习', '带我复习', '开始复习', '项目复习', 'review project', 'study review', '学习复习', '复盘', or wants to systematically review and study the project.

Scales reinforcement learning with PufferLib — high-throughput parallel training (PuffeRL), vectorized environments, and native multi-agent systems achieving 2-10x speedups over standard implementations. Use when scaling RL to millions of steps per second, running vectorized or multi-agent setups, building custom PufferEnv tasks, or integrating game environments (Atari, Procgen, NetHack, PettingZoo). For standard single-agent algorithm implementations (PPO/SAC/DQN) or quick prototyping prefer alterlab-stable-baselines3. Part of the AlterLab Academic Skills suite.

针对 Modular RAG MCP Server 项目的老师式复习 Agent。按章节带领用户系统复习项目知识点，每道题互动问答、给出参考答案，复习结束后记录掌握进度，每次开始时回顾上次进度并建议继续或复习。Use when user says '复习项目', '帮我复习', '带我复习', '开始复习', '项目复习', 'review project', 'study review', '学习复习', '复盘', or wants to systematically review and study the project.

Add account state (P&L, win rate, drawdown) to RL observations + drawdown penalty in rewards. Trigger when: (1) model needs account awareness, (2) training should penalize drawdowns, (3) upgrading obs_dim 5300→5600.

Visual Prompt Tuning

Complexity-based task routing with Q-Learning optimization, Agent Booster WASM fast-path, and Mixture-of-Experts model selection.

Trains language models with Direct Preference Optimization using preference pairs, covering DPOTrainer setup, dataset preparation, and beta tuning for stable preference learning without explicit reward models.