/agentdb-learning

name: agentdb-learning
description: "Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more. Use when building self-learning agents, implementing RL, or optimizing agent behavior through experience."

AgentDB Learning Plugins

What This Skill Does

Provides access to 9 reinforcement learning algorithms via AgentDB's plugin system. Create, train, and deploy learning plugins for autonomous agents that improve through experience. Includes offline RL (Decision Transformer), value-based learning (Q-Learning), policy gradients (Actor-Critic), and advanced techniques.

**Performance**: Train models 10-100x faster with WASM-accelerated neural inference.

Prerequisites

• Node.js 18+
• AgentDB v1.0.7+ (via agentic-flow)
• Basic understanding of reinforcement learning (recommended)

---

Quick Start with CLI

Create Learning Plugin

# Interactive wizard
npx agentdb@latest create-plugin

# Use specific template
npx agentdb@latest create-plugin -t decision-transformer -n my-agent

# Preview without creating
npx agentdb@latest create-plugin -t q-learning --dry-run

# Custom output directory
npx agentdb@latest create-plugin -t actor-critic -o ./plugins

List Available Templates

# Show all plugin templates
npx agentdb@latest list-templates

# Available templates:
# - decision-transformer (sequence modeling RL - recommended)
# - q-learning (value-based learning)
# - sarsa (on-policy TD learning)
# - actor-critic (policy gradient with baseline)
# - curiosity-driven (exploration-based)

Manage Plugins

# List installed plugins
npx agentdb@latest list-plugins

# Get plugin information
npx agentdb@latest plugin-info my-agent

# Shows: algorithm, configuration, training status

---

Quick Start with API

import { createAgentDBAdapter } from 'agentic-flow/reasoningbank';

// Initialize with learning enabled
const adapter = await createAgentDBAdapter({
  dbPath: '.agentdb/learning.db',
  enableLearning: true,       // Enable learning plugins
  enableReasoning: true,
  cacheSize: 1000,
});

// Store training experience
await adapter.insertPattern({
  id: '',
  type: 'experience',
  domain: 'game-playing',
  pattern_data: JSON.stringify({
    embedding: await computeEmbedding('state-action-reward'),
    pattern: {
      state: [0.1, 0.2, 0.3],
      action: 2,
      reward: 1.0,
      next_state: [0.15, 0.25, 0.35],
      done: false
    }
  }),
  confidence: 0.9,
  usage_count: 1,
  success_count: 1,
  created_at: Date.now(),
  last_used: Date.now(),
});

// Train learning model
const metrics = await adapter.train({
  epochs: 50,
  batchSize: 32,
});

console.log('Training Loss:', metrics.loss);
console.log('Duration:', metrics.duration, 'ms');

---

Available Learning Algorithms (9 Total)

1. Decision Transformer (Recommended)

**Type**: Offline Reinforcement Learning **Best For**: Learning from logged experiences, imitation learning **Strengths**: No online interaction needed, stable training

npx agentdb@latest create-plugin -t decision-transformer -n dt-agent

**Use Cases**:

• Learn from historical data
• Imitation learning from expert demonstrations
• Safe learning without environment interaction
• Sequence modeling tasks

**Configuration**:

{
  "algorithm": "decision-transformer",
  "model_size": "base",
  "context_length": 20,
  "embed_dim": 128,
  "n_heads": 8,
  "n_layers": 6
}

2. Q-Learning

**Type**: Value-Based RL (Off-Policy) **Best For**: Discrete action spaces, sample efficiency **Strengths**: Proven, simple, works well for small/medium problems

npx agentdb@latest create-plugin -t q-learning -n q-agent

**Use Cases**:

• Grid worlds, board games
• Navigation tasks
• Resource allocation
• Discrete decision-making

**Configuration**:

{
  "algorithm": "q-learning",
  "learning_rate": 0.001,
  "gamma": 0.99,
  "epsilon": 0.1,
  "epsilon_decay": 0.995
}

3. SARSA

**Type**: Value-Based RL (On-Policy) **Best For**: Safe exploration, risk-sensitive tasks **Strengths**: More conservative than Q-Learning, better for safety

npx agentdb@latest create-plugin -t sarsa -n sarsa-agent

**Use Cases**:

• Safety-critical applications
• Risk-sensitive decision-making
• Online learning with exploration

**Configuration**:

{
  "algorithm": "sarsa",
  "learning_rate": 0.001,
  "gamma": 0.99,
  "epsilon": 0.1
}

4. Actor-Critic

**Type**: Policy Gradient with Value Baseline **Best For**: Continuous actions, variance reduction **Strengths**: Stable, works for continuous/discrete actions

npx agentdb@latest create-plugin -t actor-critic -n ac-agent

**Use Cases**:

• Continuous control (robotics, simulations)
• Complex action spaces
• Multi-agent coordination

**Configuration**:

{
  "algorithm": "actor-critic",
  "actor_lr": 0.001,
  "critic_lr": 0.002,
  "gamma": 0.99,
  "entropy_coef": 0.01
}

5. Active Learning

**Type**: Query-Based Learning **Best For**: Label-efficient learning, human-in-the-loop **Strengths**: Minimizes labeling cost, focuses on uncertain samples

**Use Cases**:

• Human feedback incorporation
• Label-efficient training
• Uncertainty sampling
• Annotation cost reduction

6. Adversarial Training

**Type**: Robustness Enhancement **Best For**: Safety, robustness to perturbations **Strengths**: Improves model robustness, adversarial defense

**Use Cases**:

• Security applications
• Robust decision-making
• Adversarial defense
• Safety testing

7. Curriculum Learning

**Type**: Progressive Difficulty Training **Best For**: Complex tasks, faster convergence **Strengths**: Stable learning, faster convergence on hard tasks

**Use Cases**:

• Complex multi-stage tasks
• Hard exploration problems
• Skill composition
• Transfer learning

8. Federated Learning

**Type**: Distributed Learn