Results for “reinforcement”

Fixes common PyTorch bugs including percentile calculations, LayerNorm for Conv1d, and buffer edge cases in reinforcement learning and neural network code.

Train LLMs with reinforcement learning using verl (Volcano Engine RL), supporting RLHF, GRPO, PPO, and other algorithms for scalable post-training with flexible infrastructure backends.

Train reinforcement learning agents using PPO, SAC, DQN, TD3, DDPG, and A2C algorithms with a scikit-learn-like API. Supports custom Gymnasium environments, vectorized environments, callbacks, and model persistence.

SONA self-optimizing neural architecture with ReasoningBank trajectory learning, EWC++ anti-forgetting, and reinforcement learning feedback loops.

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

Train large-scale MoE models with FP8/INT4 low-precision RL, speculative decoding, and train-inference alignment using the miles framework.

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

Configure fault tolerance, straggler detection, preemption, in-process restart, and re-run state machine for Megatron Bridge training jobs.

Executes containment strategies to stop active adversary operations and prevent lateral movement during a confirmed security breach, using network segmentation, endpoint isolation, credential revocation, and access control modifications.

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.

Automated test validation, coverage checking, and quality metrics with aggressive defaults

Agent validation v4.3.0 — Make agents act effectively by disabling harmful actions, lowering gates, and injecting cross-run learning

Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.

Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.

For analysis/task/review agents using a Professional Skill on devices, firmware, edge protocols, updates, or safety; not for work without device, firmware, or physical impact.

Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR. (gstack)

Runs a data augmentation pipeline on a given input and reports pass/fail per transform, diagnosing failures against known issues.

Use this skill for auth boundaries, input validation, secrets, RLS, injection risks, destructive-action review. Trigger when the task involves security work related to Security Hardening, production implementation, audits, debugging, strategy, or validation.

Hardens Windows Active Directory environments against ransomware by configuring Group Policy Objects with AppLocker rules, Controlled Folder Access, Attack Surface Reduction rules, and lateral movement restrictions.

Use to find upgrade, seat-growth and new-use-case signals that customers give support and nobody routes anywhere. Trigger for "find upsell opportunities in support", "customers hitting plan limits", "which accounts are asking about enterprise features", expansion signals from tickets, or support-sourced pipeline.

Configures memory protection mechanisms including DEP, ASLR, CFG, and Windows Exploit Protection to harden endpoints against buffer overflows, ROP chains, and code injection.

AutoAugment: Learning Augmentation Strategies from Data

Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR. (gstack)

Land and deploy workflow. (gstack)

Land and deploy workflow. Merges the PR, waits for CI and deploy, verifies production health via canary checks. Takes over after /ship creates the PR. Use when: "merge", "land", "deploy", "merge and verify", "land it", "ship it to production". (gstack)

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

Updates AGENTS.md after a repeated verified failure. Do not use for one-off preferences or speculative rules.

Enforces bulk-safety rules, sharing model requirements, CRUD/FLS security, SOQL injection prevention, PNB test coverage, and modern Apex idioms for Salesforce development.