What problem does it solve? Building self-improving AI agents requires implementing reinforcement learning from scratch, which is complex and error-prone. This Skill provides ready-to-use templates and APIs for training agents that learn from experience using AgentDB's plugin system. ## Core Features & Use Cases - Nine RL Algorithms: Access Decision Transformer, Q-Learning, SARSA, Actor-Critic, Active Learning, Adversarial Training, Curriculum Learning, Federated Learning, and Multi-Task Learning via CLI templates or the TypeScript API. - Experience-Based Training: Store state-action-reward experiences as vector patterns, then train models with configurable epochs, batch sizes, and validation splits. - Reasoning Integration: Combine learned experiences with reasoning-based retrieval (MMR, context synthesis, memory optimization) for decision-making. - Use Case: Train a game-playing agent by logging episode steps into AgentDB, running adapter.train() over collected experiences, then retrieving suggested actions with confidence scores for new states. ## Quick Start Ask the AI to create a Decision Transformer learning plugin with AgentDB and train it on stored agent experiences.