gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2025-12-18 03:30:19 +01:00
Code Issues Projects Releases Wiki Activity

Batch RL (#238)

Browse Source
This commit is contained in:
Gal Leibovich
2019-03-19 18:07:09 +02:00
committed by GitHub
parent 4a8451ff02
commit e3c7e526c7
38 changed files with 1003 additions and 87 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
rl_coach/graph_managers/basic_rl_graph_manager.py
View File

@@ -18,6 +18,7 @@ from typing import Tuple, List
from rl_coach.base_parameters import AgentParameters, VisualizationParameters, TaskParameters, \
PresetValidationParameters
from rl_coach.environments.environment import EnvironmentParameters, Environment
from rl_coach.filters.filter import NoInputFilter, NoOutputFilter
from rl_coach.graph_managers.graph_manager import GraphManager, ScheduleParameters
from rl_coach.level_manager import LevelManager
from rl_coach.utils import short_dynamic_import
@@ -31,17 +32,28 @@ class BasicRLGraphManager(GraphManager):
def __init__(self, agent_params: AgentParameters, env_params: EnvironmentParameters,
schedule_params: ScheduleParameters,
vis_params: VisualizationParameters=VisualizationParameters(),
preset_validation_params: PresetValidationParameters = PresetValidationParameters()):
super().__init__('simple_rl_graph', schedule_params, vis_params)
preset_validation_params: PresetValidationParameters = PresetValidationParameters(),
name='simple_rl_graph'):
super().__init__(name, schedule_params, vis_params)
self.agent_params = agent_params
self.env_params = env_params
self.preset_validation_params = preset_validation_params
self.agent_params.visualization = vis_params
if self.agent_params.input_filter is None:
self.agent_params.input_filter = env_params.default_input_filter()
if env_params is not None:
self.agent_params.input_filter = env_params.default_input_filter()
else:
# In cases where there is no environment (e.g. batch-rl and imitation learning), there is nowhere to get
# a default filter from. So using a default no-filter.
# When there is no environment, the user is expected to define input/output filters (if required) using
# the preset.
self.agent_params.input_filter = NoInputFilter()
if self.agent_params.output_filter is None:
self.agent_params.output_filter = env_params.default_output_filter()
if env_params is not None:
self.agent_params.output_filter = env_params.default_output_filter()
else:
self.agent_params.output_filter = NoOutputFilter()
def _create_graph(self, task_parameters: TaskParameters) -> Tuple[List[LevelManager], List[Environment]]:
# environment loading