mirror of
https://github.com/gryf/coach.git
synced 2025-12-17 11:10:20 +01:00
39 lines
1.5 KiB
Python
39 lines
1.5 KiB
Python
from rl_coach.agents.bootstrapped_dqn_agent import BootstrappedDQNAgentParameters
|
|
from rl_coach.base_parameters import VisualizationParameters, PresetValidationParameters
|
|
from rl_coach.core_types import EnvironmentSteps
|
|
from rl_coach.environments.environment import SingleLevelSelection
|
|
from rl_coach.environments.gym_environment import Atari, atari_deterministic_v4
|
|
from rl_coach.graph_managers.basic_rl_graph_manager import BasicRLGraphManager
|
|
from rl_coach.graph_managers.graph_manager import ScheduleParameters
|
|
|
|
####################
|
|
# Graph Scheduling #
|
|
####################
|
|
|
|
schedule_params = ScheduleParameters()
|
|
schedule_params.improve_steps = EnvironmentSteps(50000000)
|
|
schedule_params.steps_between_evaluation_periods = EnvironmentSteps(250000)
|
|
schedule_params.evaluation_steps = EnvironmentSteps(135000)
|
|
schedule_params.heatup_steps = EnvironmentSteps(50000)
|
|
|
|
#########
|
|
# Agent #
|
|
#########
|
|
agent_params = BootstrappedDQNAgentParameters()
|
|
agent_params.network_wrappers['main'].learning_rate = 0.00025
|
|
|
|
###############
|
|
# Environment #
|
|
###############
|
|
env_params = Atari(level=SingleLevelSelection(atari_deterministic_v4))
|
|
|
|
########
|
|
# Test #
|
|
########
|
|
preset_validation_params = PresetValidationParameters()
|
|
preset_validation_params.trace_test_levels = ['breakout', 'pong', 'space_invaders']
|
|
|
|
graph_manager = BasicRLGraphManager(agent_params=agent_params, env_params=env_params,
|
|
schedule_params=schedule_params, vis_params=VisualizationParameters(),
|
|
preset_validation_params=preset_validation_params)
|