simpo-training

21.8k

davila7

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when you want simpler, faster training than DPO/PPO.

grpo-rl-training

21.8k

davila7

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

pufferlib

21.8k

davila7

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.

verl-rl-training

21.8k

davila7

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.

openrlhf-training

21.8k

davila7

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.

fine-tuning-with-trl

21.8k

davila7

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.

stable-baselines3

21.8k

davila7

Use this skill for reinforcement learning tasks including training RL agents (PPO, SAC, DQN, TD3, DDPG, A2C, etc.), creating custom Gym environments, implementing callbacks for monitoring and control, using vectorized environments for parallel training, and integrating with deep RL workflows. This skill should be used when users request RL algorithm implementation, agent training, environment design, or RL experimentation.

stable-baselines3

10.8k

K-Dense-AI

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.

agentdb-reinforcement-learning-training

188

aiskillstore

Train AI agents using AgentDB's 9 reinforcement learning algorithms including Q-Learning, DQN, PPO, and Actor-Critic. Build self-learning agents, implement RL training loops with experience replay, and deploy optimized models to production.

model_finetuning

39

vuralserhat86

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.

reinforcement-learning

29

omer-metin

Use when implementing RL algorithms, training agents with rewards, or aligning LLMs with human feedback - covers policy gradients, PPO, Q-learning, RLHF, and GRPOUse when ", " mentioned.

stable-baselines3

15

oimiragieo

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.

cursor-edit

10

heishia

Performs actual code modifications via the Cursor CLI. It accepts analysis/plan results and delegates code edits to the cursor-agent. Use this when actual file changes are required, such as code edits, refactoring, feature additions, or bug fixes.

verify

10

heishia

Verify results after code changes. Use when quality checks are needed after code modifications, such as reviewing changes, running tests, checking builds, and running lint checks.

analyze

10

heishia

Analyze and understand a codebase. Use when analysis is needed before modifying code, such as understanding structure, analyzing dependencies, identifying patterns, and discovering issues.

pufferlib

9

jackspace

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.

Stable Baselines3（stable-baselines3）

9

jackspace

Use this skill for reinforcement learning tasks including training RL agents (PPO, SAC, DQN, TD3, DDPG, A2C, etc.), creating custom Gym environments, implementing callbacks for monitoring and control, using vectorized environments for parallel training, and integrating with deep RL workflows. This skill should be used when users request RL algorithm implementation, agent training, environment design, or RL experimentation.

ksim-rl

7

plurigrid

RL training library for humanoid locomotion and manipulation built on MuJoCo and JAX. Provides PPO, AMP, and custom task abstractions for sim-to-real robotics policy training.

reinforcement-learning

5

pluginagentmarketplace

Q-learning, DQN, PPO, A3C, policy gradient methods, multi-agent systems, and Gym environments. Use for training agents, game AI, robotics, or decision-making systems.

rltools-training

1

chuongdlb

Configure and run RL training with rl-tools — SAC, TD3, PPO training, hyperparameters, network architecture, composable loop steps.

isaaclab-rl-training

1

chuongdlb

Trains RL policies in IsaacLab using RSL-RL, RL-Games, Stable-Baselines3, or SKRL — PPO configs, checkpoints, multi-GPU, Ray tuning.

stable-baselines3

1

iamseungpil

Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with a 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.

gpd-training-evaluation

1

chuongdlb

Stable-Baselines3 PPO training pipeline — environment setup, callbacks, reward thresholds, model saving, evaluation, inference loop.

stable-baselines3

reikiplanet

Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with a 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.