Skills and MCP tagged “reinforcement-learning”

pufferlib K-Dense-AI skill Skill for PufferLib: choose between native 5.0, PyPI 3.0.0, or pinned 4.0, validate Gymnasium contracts, adapt environments, and review checkpoints safely. Requires Python 3.10+ and native C/CUDA for training. Claude Code CX Codex Cursor +1 1,900installs stable-baselines3 K-Dense-AI skill A skill for training reinforcement learning agents with Stable Baselines3. Supports PPO, SAC, DQN and other algorithms, works with Gymnasium custom environments and vectorized rollouts. Claude Code CX Codex Cursor +1 1,900installs AgentDB Learning Plugins ruvnet skill Generates and trains reinforcement learning plugins for autonomous agents across 9 algorithms using AgentDB. Claude Code CX Codex Cursor +1 1,100installs grpo-rlvr-training Seth Hobson skill Configures GRPO and RLVR training pipelines for tasks with verifiable outcomes. Useful when evaluating models with code execution, unit tests, or strict schemas. Claude Code CX Codex Cursor 2,600installs spinning-up-deep-rl Alireza Rezvani skill A deep RL knowledge base for Claude Code, covering algorithms, policy gradients, and silent bugs. Use it when building or checking RL experiments. Claude Code 8installs