What problem does it solve? Building self-improving agents requires implementing reinforcement learning from scratch, which involves complex algorithm selection, training loops, and experience management. This Skill provides ready-to-use templates and APIs for training agents that learn from experience. ## 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 through CLI templates or a TypeScript API. - Experience Storage and Training: Store state-action-reward experiences as patterns in AgentDB, then train models with configurable epochs, batch sizes, and validation splits. - Use Case: A developer building a game-playing agent collects episode experiences during execution, stores them via insertPattern, trains a Decision Transformer model offline, and retrieves suggested actions with confidence scores at inference time. ## Quick Start Run npx agentdb@latest create-plugin -t decision-transformer -n my-agent to scaffold a learning plugin, then store experiences and call adapter.train to begin training.
