huangfu/InteractionImitation
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

More expert data

Browse Source
This commit is contained in:
ebuehrle
2021-11-04 19:54:40 +01:00
parent 081fb4e6ab
commit 071c731921
2 changed files with 3 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
scratch/etienne/intersimple/data/generate.sh
View File

@@ -11,4 +11,4 @@
#python -m expert --env=NRasterizedRouteRandomAgentLocation --min_timesteps=100000 --env_args='{width:70,height:70,m_per_px:1,map_color:128}' --policy_args='{mu:0.001}' --path='NormalizedIntersimpleExpertMu.001N100000_NRasterizedRouteRandomAgentLocationw70h70mppx1mapc128.pkl' #python -m expert --env=NRasterizedRouteRandomAgentLocation --min_timesteps=100000 --env_args='{width:70,height:70,m_per_px:1,map_color:128}' --policy_args='{mu:0.001}' --path='NormalizedIntersimpleExpertMu.001N100000_NRasterizedRouteRandomAgentLocationw70h70mppx1mapc128.pkl'
#python -m expert --env=NRasterizedRouteSpeedRandomAgentLocation --min_timesteps=10000 --env_args='{width:70,height:70,m_per_px:1,map_color:128,mu:0.001}' --policy_args='{mu:0.001}' --path='NormalizedIntersimpleExpertMu.001N10000_NRasterizedRouteSpeedRandomAgentLocationw70h70mppx1mapc128mu.001.pkl' #python -m expert --env=NRasterizedRouteSpeedRandomAgentLocation --min_timesteps=10000 --env_args='{width:70,height:70,m_per_px:1,map_color:128,mu:0.001}' --policy_args='{mu:0.001}' --path='NormalizedIntersimpleExpertMu.001N10000_NRasterizedRouteSpeedRandomAgentLocationw70h70mppx1mapc128mu.001.pkl'
#python -m data.expert --env=NRasterizedRouteSpeedRandomAgentLocation --min_timesteps=10000 --env_args='{width:70,height:70,m_per_px:1,map_color:128,mu:0.001,skip_frames:5}' --policy_args='{mu:0.001}' --path='NormalizedIntersimpleExpertMu.001N10000_NRasterizedRouteSpeedRandomAgentLocationw70h70mppx1mapc128mu.001skip5.pkl' #python -m data.expert --env=NRasterizedRouteSpeedRandomAgentLocation --min_timesteps=10000 --env_args='{width:70,height:70,m_per_px:1,map_color:128,mu:0.001,skip_frames:5}' --policy_args='{mu:0.001}' --path='NormalizedIntersimpleExpertMu.001N10000_NRasterizedRouteSpeedRandomAgentLocationw70h70mppx1mapc128mu.001skip5.pkl'
python -m data.expert --env=TLNRasterizedRouteRandomAgentLocation --min_timesteps=10000 --env_args='{width:70,height:70,m_per_px:1,mu:0.001,random_skip:True,max_episode_steps:50}' --policy_args='{mu:0.001}' --path='NormalizedIntersimpleExpertMu.001N10000_TLNRasterizedRouteRandomAgentLocationw70h70mppx1mu.001rskips50.pkl' python -m data.expert --env=TLNRasterizedRouteRandomAgentLocation --min_timesteps=100000 --env_args='{width:70,height:70,m_per_px:1,mu:0.001,random_skip:True,max_episode_steps:50}' --policy_args='{mu:0.001}' --path='NormalizedIntersimpleExpertMu.001N100000_TLNRasterizedRouteRandomAgentLocationw70h70mppx1mu.001rskips50.pkl'

6
scratch/etienne/intersimple/gail_options_image_random_location.py
View File

@@ -5,13 +5,11 @@ sys.path.append('../../../')
from src.discriminator import CnnDiscriminatorFlatAction from src.discriminator import CnnDiscriminatorFlatAction
from imitation.algorithms import adversarial from imitation.algorithms import adversarial
import stable_baselines3 import stable_baselines3
from intersim.envs import NRasterizedRouteRandomAgentLocation
import pickle import pickle
import imitation.data.rollout as rollout import imitation.data.rollout as rollout
import tempfile import tempfile
import pathlib import pathlib
from imitation.util import logger from imitation.util import logger
from stable_baselines3.common.env_util import make_vec_env
from tqdm import tqdm from tqdm import tqdm
from src.policies.options import OptionsCnnPolicy from src.policies.options import OptionsCnnPolicy
from src.gail.train import flatten_transitions from src.gail.train import flatten_transitions
@@ -56,7 +54,7 @@ def train(
options=ALL_OPTIONS, options=ALL_OPTIONS,
discriminator=imitation_discriminator(discriminator), discriminator=imitation_discriminator(discriminator),
discount=discount, discount=discount,
ll_buffer_capacity=expert_batch_size, ll_buffer_capacity=generator_total_steps*10,
) )
generator = stable_baselines3.PPO( generator = stable_baselines3.PPO(
OptionsCnnPolicy, OptionsCnnPolicy,
@@ -100,7 +98,7 @@ def evaluate():
# %% # %%
if __name__ == '__main__': if __name__ == '__main__':
with open("data/NormalizedIntersimpleExpertMu.001N10000_TLNRasterizedRouteRandomAgentLocationw70h70mppx1mu.001rskips50.pkl", "rb") as f: with open("data/NormalizedIntersimpleExpertMu.001N100000_TLNRasterizedRouteRandomAgentLocationw70h70mppx1mu.001rskips50.pkl", "rb") as f:
trajectories = pickle.load(f) trajectories = pickle.load(f)
transitions = rollout.flatten_trajectories(trajectories) transitions = rollout.flatten_trajectories(trajectories)
train(transitions) train(transitions)