Reinforcement Learning skills

P

PufferLib

k-dense-ai

Guidance for reinforcement learning environments and policies.

Stable Baselines3

k-dense-ai

Implement and train reinforcement learning agents with ease.

Fine-Tuning with TRL

davila7

Align language models with human preferences using reinforcement learning.

Launch NeMo-RL

nvidia

Efficiently manage NeMo-RL recipes on Kubernetes.

B

Brev Etiquette

nvidia

Optimize storage and workflow for NeMo-RL agents.

TRL Fine-Tuning

nousresearch

Align language models with human preferences using TRL.

GRPO & RLVR Training

wshobson

Enhance model reasoning with verifiable rewards.

Torchforge RL Training

davila7

Streamline your PyTorch-native reinforcement learning workflows.

Miles RL Training

davila7

Enterprise-grade reinforcement learning for large models.

AgentDB Learning Plugins

ruvnet

Create and train AI learning plugins with ease.

ReasoningBank with AgentDB

ruvnet

Accelerate adaptive learning for self-learning agents.

G

GRPO/RL Training

davila7

Fine-tune models with structured output and custom rewards.

Autonomous NeMo-RL research agent workflow for directed hypothesis testing and open-ended discovery. Guides agents through the full experiment lifecycle: understanding recipes and environments, wiring RL or NeMo-gym runs, launching reproducible baselines and iterations, analyzing results, preserving human oversight, and using git plus TSV logs as the research ledger. Do NOT use for: bug fixes, code review, documentation, refactoring, dependency updates, or single-file changes.

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.

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.

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.