Skip to content

Training your Agent ‚Äč

When you have finished building your agent, it is time to begin training.

The train_iters parameter defines the number of training cycles in your training session. One training cycle is typically about 1000 agent decisions.

The trainer.train(agent, ) method call invokes the training for your agent.

python
trainer.train(agent, train_iters=500)

After we add this call, we have all the required pieces (sensors, perceptors, scenarios, and skills) of our agent and are ready to train.

python
from composabl import Agent, Skill, Sensor, Perceptor, Scenario, Trainer

from .teaching import IncrementTeacher, DecrementTeacher, TargetTeacher
from .scenarios import increment_scenarios, decrement_scenarios, target_scenarios
from .sensors import sensors
from .perceptors import perceptors

increment_skill = Skill("increment", IncrementTeacher)
for scenario_dict in increment_scenarios:
    scenario = Scenario(scenario_dict)
    increment_skill.add_scenario(scenario)

decrement_skill = Skill("decremement", DecrementTeacher)
for scenario_dict in decrement_scenarios:
    scenario = Scenario(scenario_dict)
    decrement_skill.add_scenario(scenario)

target_skill = Skill("target", TargetTeacher)
for scenario_dict in target_scenarios:
    scenario = Scenario(scenario_dict)
    target_skill.add_scenario(scenario)

config = {
    "target": {
        "docker": {
            "image": "composabl/sim-demo:latest"
        }
    },
    "env": {
        "name": "sim-demo",
    },
    "license": "<This is your license key>",
    "training": {},
}

trainer = Trainer(config)
agent = Agent()
agent.add_sensors(sensors)
agent.add_perceptors(perceptors)

agent.add_skill(increment_skill)
agent.add_skill(decrement_skill)
agent.add_selector_skill(target_skill, [increment_skill, decrement_skill], fixed_order=False, fixed_order_repeat=True)

trainer.train(agent, train_iters=1000)

Call the agent.py Python file from the command line to start training.

bash
python agent.py