gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2025-12-17 19:20:19 +01:00
Code Issues Projects Releases Wiki Activity

human agent will exit when human control not supported by environment; jupyter notebooks fixes

Browse Source
This commit is contained in:
Gal Novik
2018-09-17 15:59:00 +03:00
parent bb76c5c726
commit abaa58b559
4 changed files with 10 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
rl_coach/environments/gym_environment.py
View File

@@ -329,6 +329,8 @@ class GymEnvironment(Environment):
self.key_to_action = {}
if hasattr(self.env.unwrapped, 'get_keys_to_action'):
self.key_to_action = self.env.unwrapped.get_keys_to_action()
else:
screen.error("Error: Environment {} does not support human control.".format(self.env), crash=True)
# initialize the state by getting a new state from the environment
self.reset_internal_state(True)

2
tutorials/1. Implementing an Algorithm.ipynb
View File

@@ -348,7 +348,7 @@
"metadata": {},
"source": [
"# Running the Preset\n",
"(this is normally done from command line by running ```python coach.py -p atari_categorical_dqn ... ```)"
"(this is normally done from command line by running ```coach -p Atari_C51 ... ```)"
]
},
{

4
tutorials/2. Adding an Environment.ipynb
View File

@@ -28,7 +28,7 @@
"outputs": [],
"source": [
"import os\n",
"os.environ['DISABLE_MUJOCO_RENDERING'] = '1'\n",
"#os.environ['DISABLE_MUJOCO_RENDERING'] = '1'\n",
"\n",
"import sys\n",
"module_path = os.path.abspath(os.path.join('..'))\n",
@@ -334,7 +334,7 @@
" schedule_params=schedule_params, vis_params=vis_params)\n",
"\n",
"graph_manager.env_params.level.select('walker:walk')\n",
"#graph_manager.visualization_parameters.render = True\n",
"graph_manager.visualization_parameters.render = True\n",
"\n",
"\n",
"log_path = '../experiments/control_suite_walker_ddpg'\n",

8
tutorials/3. Implementing a Hierarchical RL Graph.ipynb
View File

@@ -163,7 +163,8 @@
"outputs": [],
"source": [
"from rl_coach.architectures.tensorflow_components.architecture import Dense\n",
"from rl_coach.base_parameters import VisualizationParameters, EmbeddingMergerType, EmbedderScheme, InputEmbedderParameters\n",
"from rl_coach.base_parameters import VisualizationParameters, EmbeddingMergerType, EmbedderScheme\n",
"from rl_coach.architectures.tensorflow_components.embedders.embedder import InputEmbedderParameters\n",
"from rl_coach.memories.episodic.episodic_hindsight_experience_replay import HindsightGoalSelectionMethod, \\\n",
" EpisodicHindsightExperienceReplayParameters\n",
"from rl_coach.memories.episodic.episodic_hrl_hindsight_experience_replay import \\\n",
@@ -344,7 +345,8 @@
"source": [
"graph_manager = HRLGraphManager(agents_params=agents_params, env_params=env_params,\n",
" schedule_params=schedule_params, vis_params=vis_params,\n",
" consecutive_steps_to_run_each_level=EnvironmentSteps(40))"
" consecutive_steps_to_run_each_level=EnvironmentSteps(40))\n",
"graph_manager.visualization_parameters.render = True"
]
},
{
@@ -360,7 +362,7 @@
"metadata": {},
"outputs": [],
"source": [
"from base_parameters import TaskParameters, Frameworks\n",
"from rl_coach.base_parameters import TaskParameters, Frameworks\n",
"\n",
"log_path = '../experiments/pendulum_hac'\n",
"if not os.path.exists(log_path):\n",