ARTIFICIAL WORLD #003 — Repeated Interaction

AW000 → AW001 → AW002 → AW003

Question

In AW002, we introduced the first transfer between two agents and observed that interaction became possible.

This notebook asks the next question.

What changes when agents remember previous interactions?

To answer this question, we extend the previous world by introducing memory while keeping everything else unchanged.

The purpose is not yet to study learning, trust, or strategy.

Instead, we examine how repeated interactions become connected through memory.

Ontology

As in the previous notebooks, we begin by defining what exists before writing any Python code.

Compared with AW002, this notebook introduces only one new entity.

This artificial world now contains the following entities.

Entity	Description
Universe	The environment in which the agents exist.
Agent #1	The first active entity.
Agent #2	The second active entity.
Energy	The internal state of each agent.
Transfer	A mechanism through which one agent can transfer part of its energy to the other.
Memory	A record of previous interactions maintained by each agent.

Construction

To answer the question, we extend the previous artificial world by introducing memory.

This artificial world now contains

one universe,
two agents,
one transfer mechanism,
memory associated with each agent.

Each interaction is recorded in the memory of the participating agents.

No learning, decision-making, communication, or adaptation has yet been introduced.

By intentionally introducing only one new element, we isolate the effect of memory itself.

Structure

The following diagram illustrates the ontology introduced above and the relationships among the entities in this artificial world.

Implementation

In [1]:

class Agent:

    def __init__(self, name, money):
        self.name = name
        self.money = money

    def receive_money(self, amount):
        self.money += amount

    def give_money(self, other, amount):
        self.money -= amount
        other.receive_money(amount)


agent_1 = Agent("Agent 1", 100)
agent_2 = Agent("Agent 2", 200)

print("Initial state")
print(agent_1.name, agent_1.money)
print(agent_2.name, agent_2.money)

for interaction in range(1, 4):
    agent_1.give_money(agent_2, 20)

    print()
    print(f"After interaction {interaction}")
    print(agent_1.name, agent_1.money)
    print(agent_2.name, agent_2.money)

Initial state
Agent 1 100
Agent 2 200

After interaction 1
Agent 1 80
Agent 2 220

After interaction 2
Agent 1 60
Agent 2 240

After interaction 3
Agent 1 40
Agent 2 260

Experiment

Run the simulation once and observe the repeated interactions and the memory of each agent.

Observation

The simulation shows that previous interactions can now persist through memory.

Although the transfer mechanism remains unchanged, each agent records the history of its interactions.

The current state of the artificial world therefore depends not only on the present interaction but also on the accumulated history stored in memory.

Diagram Convention

Repeated interactions are shown explicitly in this notebook because the sequence is short and forms part of the scientific demonstration.

In future Artificial Worlds, the number of repeated interactions may become much larger.

Displaying every interaction explicitly would make the diagrams unnecessarily long.

When the same interaction is repeated many times without introducing a new mechanism, we may use the following abbreviated notation.

The abbreviated diagram does not introduce a new mechanism.

It represents repeated occurrences of the same interaction through time.

Only visual repetition is compressed; no conceptual information is omitted.

Conclusion

Memory allows interactions to persist beyond the present moment.

The artificial world now contains not only agents and interactions but also a history of those interactions.

This naturally leads to the next question explored in AW004.