vafali / development-of-deep-reinforcement-learning-policy-in-a-parking-simulated-environment Goto Github PK
View Code? Open in Web Editor NEWDevelopment of Deep Reinforcement Learning Policy in a Parking Simulated Environment (DDPG)
Development of Deep Reinforcement Learning Policy in a Parking Simulated Environment (DDPG)
How can I add a parallel parking spot to the parking lot map and train it, as currently all are perpendicular parking spots?
Thanks a lot!
Hi, would u like to share your pretrained model for test? Thanks a lot
Would u like to share the requirements, tks!
Select one option:
Play with trained model (press 0)
Train pretrained model (press 1)
Train new model (press 2)
Your answer: 2
Enter the number of total episodes (for default [1000] press Enter):
Your answer: 1000
Select model for training:
Only throttle action model (press 1)
Throttle and steer actions model (press 2)
Your answer: 2
Select spawning method:
Always in front of goal (press 1)
Randomly somewhere around goal (press 2)
Your answer: 2
Write the name of this training:
Your answer: model2312
Model: "Actor_Model"
input_1 (InputLayer) [(None, 16)] 0
batch_normalization (BatchN (None, 16) 64
ormalization)
dense (Dense) (None, 512) 8704
dense_1 (Dense) (None, 256) 131328
dense_2 (Dense) (None, 2) 514
=================================================================
Total params: 140,610
Trainable params: 140,578
Non-trainable params: 32
None
Model: "Critic_Model"
input_2 (InputLayer) [(None, 16)] 0 []
input_3 (InputLayer) [(None, 2)] 0 []
batch_normalization_1 (BatchNo (None, 16) 64 ['input_2[0][0]']
rmalization)
batch_normalization_2 (BatchNo (None, 2) 8 ['input_3[0][0]']
rmalization)
dense_3 (Dense) (None, 64) 1088 ['batch_normalization_1[0][0]']
dense_5 (Dense) (None, 64) 192 ['batch_normalization_2[0][0]']
dense_4 (Dense) (None, 128) 8320 ['dense_3[0][0]']
dense_6 (Dense) (None, 128) 8320 ['dense_5[0][0]']
concatenate (Concatenate) (None, 256) 0 ['dense_4[0][0]',
'dense_6[0][0]']
dense_7 (Dense) (None, 256) 65792 ['concatenate[0][0]']
dense_8 (Dense) (None, 256) 65792 ['dense_7[0][0]']
dense_9 (Dense) (None, 1) 257 ['dense_8[0][0]']
==================================================================================================
Total params: 149,833
Trainable params: 149,797
Non-trainable params: 36
None
-----------------Start of training process---------------
Episode * 1 * Episodic Reward is ==> -960.076346052685 <<<>>> Agent crashed :(
Episode * 2 * Episodic Reward is ==> -993.8164936226331 <<<>>> Agent crashed :(
Episode * 3 * Episodic Reward is ==> -498.04477143016993 <<<>>> Agent moved far away from goal :(
[Errno 2] No such file or directory: 'D:\01_caijia\03_program\ddpg\CARLA_0.9.10\PythonAPI\ddpgcarla/recordings/throttle_and_steer/random_spawn/model2312/4.csv'
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.