「reinforcement learning」の検索結果

Post-train LLMs with TRL (Transformers Reinforcement Learning) — SFT, DPO, GRPO, KTO, and reward-model training. Use when writing or debugging training code with the TRL Python API or the trl CLI.

日本語の概要は準備中です。原文の説明を表示しています。

Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, model selection/leaderboards and model persistence. Use for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.

日本語の概要は準備中です。原文の説明を表示しています。

Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. Use for standard RL experiments, quick prototyping, and well-documented algorithm implementations. Best for single-agent RL with Gymnasium environments. For high-performance parallel training, multi-agent systems, or custom vectorized environments, use pufferlib instead.

日本語の概要は準備中です。原文の説明を表示しています。

This skill should be used when working with reinforcement learning tasks including high-performance RL training, custom environment development, vectorized parallel simulation, multi-agent systems, or integration with existing RL environments (Gymnasium, PettingZoo, Atari, Procgen, etc.). Use this skill for implementing PPO training, creating PufferEnv environments, optimizing RL performance, or developing policies with CNNs/LSTMs.

日本語の概要は準備中です。原文の説明を表示しています。

Use when training, evaluating, or exporting Workflow policies with online RSL-RL or RLinf, including RL checkpoint and Workflow handoff.

日本語の概要は準備中です。原文の説明を表示しています。

Builds, runs, debugs, and operates applications on AWS Lambda MicroVMs — Firecracker-isolated, snapshot-resumable serverless compute environments running inside a container with up to 8 hr lifetimes. Applicable when workloads need strong isolation between tenants, isolated serverless compute, sandbox compute, or secure multi-tenant execution. Also suited for AI/agent code-execution sandboxes, interactive code playgrounds and notebooks (Jupyter, REPLs, dev environments running user-supplied code), reinforcement-learning environments, multi-tenant CI executors and build runners, sessionful game or simulation servers, or isolated security scanners. Also applicable when the workload needs long-lived sessions, a real port-listening server (gRPC, WebSocket, custom TCP protocols), state preserved across periods of inactivity (suspend/resume), container-level access (FUSE, eBPF, custom syscalls), or session-affine routing.

日本語の概要は準備中です。原文の説明を表示しています。

Diagnostic guide for RL-based post-training of language models (GRPO, PPO, REINFORCE, DPO). Use proactively when debugging a training pipeline that shows no improvement, loss anomalies, reward stagnation, NaN gradients, or other unexpected behavior during reinforcement learning fine-tuning. Work through all pipeline stages — reward, advantages, log-probs, loss, generation/decoding — before concluding the diagnosis is complete; stopping after one or two fixes is a common failure mode. Covers log-probability math, advantage estimation, numerical stability, reward processing, and generation/decoding pipeline issues.

日本語の概要は準備中です。原文の説明を表示しています。

Reference for the TRL (Transformer Reinforcement Learning) library codebase. Use proactively before reading or editing any file under `trl/` so you have the intended contracts and invariants in mind, not just what the current code says. Covers trainer hierarchy (SFT, DPO, GRPO, KTO), shared utility functions (selective_log_softmax, decode_and_strip_padding, padding helpers), configuration system, model wrappers, and how data flows through any TRL trainer.

日本語の概要は準備中です。原文の説明を表示しています。

Use when positioning an AAMAS submission against multiagent, game-theory, and reinforcement-learning literature spread across AAMAS, AAAI, IJCAI, NeurIPS, ICML, EC, and JAAMAS, including arXiv and workshop versions, concurrent submissions, prior conference versions, and the cross-community citation coverage AAMAS reviewers expect.

日本語の概要は準備中です。原文の説明を表示しています。

Designs novel molecules using REINVENT 4 (de novo, scaffold decoration, linker design, R-group, molecular optimization), MolMIM, Diffusion-based generators (DiGress, DiffSMol), and JT-VAE with explicit handling of multi-parameter optimization (MPO), goal-directed scoring functions, transfer/reinforcement/curriculum learning, synthetic accessibility scoring, and chemical space exploration vs exploitation. Use when designing new chemical matter against a target, decorating a scaffold, linking fragments, or optimizing a hit for multiple ADMET / activity properties simultaneously.

日本語の概要は準備中です。原文の説明を表示しています。

Build, run, debug, and operate applications on AWS Lambda MicroVMs — Firecracker-isolated, snapshot-resumable serverless compute environments that run inside a container with up to 8-hour lifetimes. Triggers on: Lambda MicroVMs, Firecracker isolation, snapshot-resumable compute, suspend/resume, sandboxed or untrusted code execution, AI/agent code-execution sandboxes, interactive code playgrounds and notebooks (Jupyter, REPLs), reinforcement-learning environments, multi-tenant CI executors and build runners, sessionful game or simulation servers, isolated security scanners, long-lived sessions, or port-listening servers (gRPC, WebSocket, custom TCP). For standard event-driven Lambda functions, use the aws-lambda skill instead.

日本語の概要は準備中です。原文の説明を表示しています。

Use when the user wants to optimize configurable system parameters against a measurable scalar objective, especially for model training, inference, quantitative strategies, reinforcement learning, scientific workflows, or other expensive black-box evaluations where reading the project can improve trial selection.

日本語の概要は準備中です。原文の説明を表示しています。

Train and optimize AI agents using Microsoft's Agent Lightning framework with reinforcement learning. Use when setting up agent training, instrumenting agents with tracing, configuring LightningStore, implementing reward functions, or optimizing prompts with RL/APO algorithms.

日本語の概要は準備中です。原文の説明を表示しています。

Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning). Supports SFT, DPO, GRPO, KTO, RLOO and Reward Model training via CLI commands.

日本語の概要は準備中です。原文の説明を表示しています。

Reinforcement learning for trade execution optimization including order splitting, adaptive timing, and impact minimization

日本語の概要は準備中です。原文の説明を表示しています。

Use DreamerV2 2.2.0 for TensorFlow world-model reinforcement-learning training, custom Gym integration, typed experiment configuration, replay/checkpoint management, and JSONL/TensorBoard evaluation.

日本語の概要は準備中です。原文の説明を表示しています。

Use DreamerV3 for world-model reinforcement learning training, embodied environment dataflow, JAX model internals, result operations, and troubleshooting.

日本語の概要は準備中です。原文の説明を表示しています。

Use CleanRL's single-file reinforcement learning scripts, evaluation utilities, experiment operations, and repository maintenance workflows safely.

日本語の概要は準備中です。原文の説明を表示しています。

Use AgileRL for reinforcement learning workflows: classical RL training, evolutionary HPO, evolvable networks, multi-agent PettingZoo training, offline/bandit data, and LLM fine-tuning.

日本語の概要は準備中です。原文の説明を表示しています。

Guide agents through AgiBot X1 humanoid reinforcement-learning training, checkpoint playback, policy export, and MuJoCo sim2sim workflows with verified configuration contracts and explicit Isaac Gym limits.

日本語の概要は準備中です。原文の説明を表示しています。

Use AReaL for large-scale asynchronous LLM reinforcement learning, agentic RL, distributed post-training, inference/agent services, backend planning, and customization workflows.

日本語の概要は準備中です。原文の説明を表示しています。

Route AI-Optimizer reinforcement-learning collection tasks across model-based RL, easy-MARL, offline RL, safe command builders, and repository limitations.

日本語の概要は準備中です。原文の説明を表示しています。

Route Acme reinforcement-learning framework tasks across core loops, replay/data, JAX agents, and TensorFlow/Sonnet agents.

日本語の概要は準備中です。原文の説明を表示しています。

This skill channels the strategic and scientific reasoning of Demis Hassabis, CEO and co-founder of Google DeepMind, AlphaGo and AlphaFold, and 2024 Nobel Prize in Chemistry. Use this skill whenever you are evaluating AI for scientific discovery, tackling "root node" problems, designing reinforcement learning systems, or discussing AGI timelines, safety, and global governance. Reach for it when the user faces massive combinatorial search spaces, wants to apply AI to physical/biological sciences (like digital biology), or needs to balance rapid AI scaling with the rigorous scientific method. Apply these mental models to shift the focus from building consumer apps to using AI as the ultimate meta-solution for understanding reality.

日本語の概要は準備中です。原文の説明を表示しています。