gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2025-12-18 19:50:17 +01:00
Code Issues Projects Releases Wiki Activity

pre-release 0.10.0

Browse Source
This commit is contained in:
Gal Novik
2018-08-13 17:11:34 +03:00
parent d44c329bb8
commit 19ca5c24b1
485 changed files with 33292 additions and 16770 deletions
Download Patch File Download Diff File Expand all files Collapse all files

47
rl_coach/presets/Atari_NEC.py Normal file
View File

@@ -0,0 +1,47 @@
from rl_coach.base_parameters import VisualizationParameters, PresetValidationParameters
from rl_coach.environments.environment import SingleLevelSelection, SelectedPhaseOnlyDumpMethod, MaxDumpMethod
from rl_coach.environments.gym_environment import Atari, AtariInputFilter, atari_deterministic_v4
from rl_coach.graph_managers.basic_rl_graph_manager import BasicRLGraphManager
from rl_coach.graph_managers.graph_manager import ScheduleParameters
from rl_coach.agents.nec_agent import NECAgentParameters
from rl_coach.core_types import TrainingSteps, EnvironmentEpisodes, EnvironmentSteps, RunPhase
####################
# Graph Scheduling #
####################
schedule_params = ScheduleParameters()
schedule_params.improve_steps = EnvironmentSteps(10000000)
schedule_params.steps_between_evaluation_periods = EnvironmentEpisodes(100)
schedule_params.evaluation_steps = EnvironmentEpisodes(3)
schedule_params.heatup_steps = EnvironmentSteps(2000)
#########
# Agent #
#########
agent_params = NECAgentParameters()
agent_params.network_wrappers['main'].learning_rate = 0.00001
agent_params.input_filter = AtariInputFilter()
agent_params.input_filter.remove_reward_filter('clipping')
###############
# Environment #
###############
env_params = Atari()
env_params.level = SingleLevelSelection(atari_deterministic_v4)
env_params.random_initialization_steps = 1
vis_params = VisualizationParameters()
vis_params.video_dump_methods = [SelectedPhaseOnlyDumpMethod(RunPhase.TEST), MaxDumpMethod()]
vis_params.dump_mp4 = False
########
# Test #
########
preset_validation_params = PresetValidationParameters()
preset_validation_params.trace_test_levels = ['breakout', 'pong', 'alien']
graph_manager = BasicRLGraphManager(agent_params=agent_params, env_params=env_params,
schedule_params=schedule_params, vis_params=vis_params,
preset_validation_params=preset_validation_params)