AI Agents with LangChain & Autonomous Workflows · レッスン

エージェントの認知アーキテクチャ

人間らしい推論や学習プロセスをAIエージェントでモデル化する、SOARやACT-Rなどの確立された認知アーキテクチャを詳しく学びます。

レッスン 4/612 ステップ

「エージェントの認知アーキテクチャ」はCoddyKit上の無料AI Agents with LangChain & Autonomous Workflowsレッスンです。これはレッスン4/6です。下記で完全なレッスンを無料で読むことができます。その後、ブラウザ内の組み込みコードエディタと24時間対応のAIチューターでハンズオン演習できます。これはAI Agents with LangChain & Autonomous Workflows学習パスの一部であり、ウェブとCoddyKitアプリ全体で進捗が同期されます。 AI Agents with LangChain & Autonomous Workflowsコースには全6レッスンが含まれています。

このレッスンの一部はまだ翻訳されておらず、英語で表示されています。

Intro to Cognitive Agents

Welcome! Today, we'll explore Cognitive Architectures. These aren't just simple programs; they're frameworks designed to mimic human-like reasoning, learning, and decision-making in AI agents.

They bridge the gap between reactive agents and truly intelligent systems capable of complex problem-solving.

Why Cognitive Architectures?

Simple agents react to immediate percepts. But what if an agent needs to plan, learn from mistakes, or understand complex situations?

Human-like Intelligence: Model how humans think.
General Problem Solving: Tackle diverse tasks, not just one.
Learning & Adaptation: Improve performance over time.
Robustness: Handle unexpected situations.

Core Components of Cognition

Most cognitive architectures share common building blocks, inspired by human psychology:

Perceptual System: How the agent "sees" the world.
Memory Systems: Short-term (working) and long-term knowledge.
Decision-Making: How the agent chooses its next action.
Motor System: How the agent acts on the world.

SOAR: State, Operator, Result

SOAR (State, Operator, And Result) is a classic cognitive architecture. It views all intelligence as a continuous process of problem-solving, represented as searching through a state space.

SOAR operates in decision cycles, constantly choosing operators to apply to the current state to reach a desired result.

SOAR's Working Memory

SOAR's working memory holds the agent's current understanding of the world, its goals, and the current problem state. It's temporary and constantly updated.

Think of it as the agent's "consciousness" at any given moment. Here's a simplified representation:

public class SoarWorkingMemory {
  String goal;
  String currentState;
  boolean obstacleDetected;

  public SoarWorkingMemory(String goal, String state) {
    this.goal = goal;
    this.currentState = state;
    this.obstacleDetected = false;
  }

  public void updateState(String newState) {
    this.currentState = newState;
  }

  public String toString() {
    return "Goal: " + goal + ", State: " + currentState +
           ", Obstacle: " + obstacleDetected;
  }

  public static void main(String[] args) {
    SoarWorkingMemory wm = new SoarWorkingMemory("ReachExit", "StartRoom");
    System.out.println(wm);
    wm.updateState("Corridor");
    System.out.println(wm);
  }
}

SOAR's Production Rules

SOAR uses production rules (if-then rules) in its long-term memory to propose and select operators. When a rule's if condition matches the working memory, its then part proposes an action or modifies the state.

This example shows a simple rule for moving an agent:

public class SoarProductionRule {
  public static void main(String[] args) {
    String currentState = "near_door";
    String goal = "exit_room";

    System.out.println("Current State: " + currentState);
    System.out.println("Goal: " + goal);

    // A simple SOAR-like production rule
    if (currentState.equals("near_door") && goal.equals("exit_room")) {
      System.out.println("Rule Fired: Propose 'open_door_operator'");
      System.out.println("Action: Agent opens the door.");
      currentState = "door_open"; // State update
    } else {
      System.out.println("No matching rule fired.");
    }
    System.out.println("New State: " + currentState);
  }
}

SOAR's Learning: Chunking

A unique feature of SOAR is chunking. When the agent encounters an impasse (a situation where it can't decide what to do), it enters a sub-state to resolve it.

Once the impasse is resolved, SOAR "chunks" the experience, creating a new production rule that directly solves that type of impasse in the future. This is how SOAR learns!

ACT-R: Adaptive Control of Thought

ACT-R (Adaptive Control of Thought—Rational) is another prominent cognitive architecture. It's designed to model human cognition at a finer grain, focusing on psychological data and predicting human behavior.

ACT-R emphasizes a modular structure, with distinct memory systems and processes working together.

ACT-R's Memory Modules

ACT-R has several key modules, including:

Declarative Memory: Stores factual knowledge (e.g., "Paris is the capital of France") as discrete units called chunks.
Procedural Memory: Stores "how-to" knowledge (e.g., "how to tie a shoe") as production rules.
Goal Module: Manages the agent's current goals.
Imaginal Module: Holds temporary problem representations.

Activation & Utility in ACT-R

Unlike SOAR's pure rule-matching, ACT-R's modules interact based on activation and utility:

Activation: Chunks in declarative memory have an activation level, influencing how quickly they can be retrieved. More relevant or recent chunks have higher activation.
Utility: Production rules in procedural memory have a utility value, reflecting their past success. Rules with higher utility are more likely to be chosen.

Cognitive Arch. Check

Let's check your understanding of these cognitive architectures.

対話的なレッスンで答える

Recap: Cognitive Agents

We've explored Cognitive Architectures, frameworks that aim for human-like intelligence. We looked at:

SOAR: Problem-solving as search, using production rules and learning via chunking.
ACT-R: A modular system with declarative and procedural memory, guided by activation and utility.

These architectures provide powerful models for building agents that can reason, learn, and adapt in complex ways.

無料で開始

AI チューターと学ぶ AI Agents with LangChain & Autonomous Workflows — 無料

ブラウザでリアルコードを書いて実行し、24/7 の AI チューターから瞬時にサポートを受け、ウェブまたはアプリで続きから学習できます。

コース: 12
レッスン: 50

無料で学習を始めるコース全体を表示

よくある質問

「エージェントの認知アーキテクチャ」レッスンは無料ですか？

はい。「エージェントの認知アーキテクチャ」の完全なテキストはこのウェブで無料で読めます。インタラクティブに演習し（組み込みコードエディタと24時間対応のAIチューター）、AI Agents with LangChain & Autonomous Workflowsコースの残りをアンロックするには、CoddyKit PROにアップグレードしてください。 AI Agents with LangChain & Autonomous Workflowsコースには全6レッスンが含まれています。

「エージェントの認知アーキテクチャ」で何を学びますか？

人間らしい推論や学習プロセスをAIエージェントでモデル化する、SOARやACT-Rなどの確立された認知アーキテクチャを詳しく学びます。ブラウザで直接実行するハンズオンコードでAI Agents with LangChain & Autonomous Workflowsを演習し、24時間対応のAIチューターがレッスンを進める中での質問に答えます。

AI Agents with LangChain & Autonomous Workflowsを始めるのに経験は必要ですか？

事前経験は必要ありません。CoddyKitのAI Agents with LangChain & Autonomous Workflowsは初級者から上級者向けに構成されているため、ここから始めるか最初から始めて、自分のペースで進むことができます。これはレッスン4/6です。

「エージェントの認知アーキテクチャ」レッスンにはどのくらい時間がかかりますか？

ほとんどのCoddyKitレッスンは約5～10分かかります。各レッスンはコンパクトでインタラクティブなので、着実に進歩し、ウェブとアプリ全体で正確に前回の場所から再開できます。

このAI Agents with LangChain & Autonomous Workflowsレッスンでコードを書いて実行できますか？

はい。すべてのAI Agents with LangChain & Autonomous Workflowsレッスンに組み込みコードエディタが含まれているため、ブラウザでリアルコードを書いて実行し、即座のAIフィードバックを取得できます。ローカル設定は不要です。

このコースのすべてのレッスン

← AI Agents with LangChain & Autonomous Workflowsに戻る