mirror of
https://github.com/gryf/coach.git
synced 2025-12-17 11:10:20 +01:00
47 lines
1.9 KiB
Python
47 lines
1.9 KiB
Python
from rl_coach.agents.n_step_q_agent import NStepQAgentParameters
|
|
from rl_coach.base_parameters import VisualizationParameters, PresetValidationParameters
|
|
from rl_coach.core_types import TrainingSteps, EnvironmentEpisodes, EnvironmentSteps
|
|
from rl_coach.environments.gym_environment import GymVectorEnvironment
|
|
from rl_coach.filters.filter import InputFilter
|
|
from rl_coach.filters.reward.reward_rescale_filter import RewardRescaleFilter
|
|
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 = TrainingSteps(10000000000)
|
|
schedule_params.steps_between_evaluation_periods = EnvironmentEpisodes(10)
|
|
schedule_params.evaluation_steps = EnvironmentEpisodes(1)
|
|
schedule_params.heatup_steps = EnvironmentSteps(0)
|
|
|
|
#########
|
|
# Agent #
|
|
#########
|
|
agent_params = NStepQAgentParameters()
|
|
|
|
agent_params.algorithm.discount = 0.99
|
|
agent_params.network_wrappers['main'].learning_rate = 0.0001
|
|
agent_params.algorithm.num_steps_between_copying_online_weights_to_target = EnvironmentSteps(100)
|
|
agent_params.input_filter = InputFilter()
|
|
agent_params.input_filter.add_reward_filter('rescale', RewardRescaleFilter(1/200.))
|
|
|
|
###############
|
|
# Environment #
|
|
###############
|
|
env_params = GymVectorEnvironment(level='CartPole-v0')
|
|
|
|
########
|
|
# Test #
|
|
########
|
|
preset_validation_params = PresetValidationParameters()
|
|
preset_validation_params.test = True
|
|
preset_validation_params.min_reward_threshold = 150
|
|
preset_validation_params.max_episodes_to_achieve_reward = 200
|
|
preset_validation_params.num_workers = 8
|
|
|
|
graph_manager = BasicRLGraphManager(agent_params=agent_params, env_params=env_params,
|
|
schedule_params=schedule_params, vis_params=VisualizationParameters(),
|
|
preset_validation_params=preset_validation_params)
|