Comments (5)
LocLePhuoc
commented on August 23, 2024
I encountered the same problem. The agent won't move even though the simulation is running.
from hands-on-intelligent-agents-with-openai-gym.
praveen-palanisamy
commented on August 23, 2024
[Edited]
On a second look at your log, I figured that you are running the trained agent in train mode. If you want to use the trained model for testing the agent to see how well it drives, you should use the --test command-line argument as mentioned in the README here.
This is the command:
python a2c_agent.py --env Carla-v0 --test --render
from hands-on-intelligent-agents-with-openai-gym.
Amakri1020
commented on August 23, 2024
That's true, but it is still loading the trained A2C_Carla-v0.ptm agent for the train mode correct? It has the same behaviour in test mode unfortunately =\ it simply sits there not taking any actions.
from hands-on-intelligent-agents-with-openai-gym.
praveen-palanisamy
commented on August 23, 2024
In that case, the agent needs to be trained more.
If you are observing the same behavior for several episodes, its very likely that the trained agent "brain"/model seems to have learnt only so much (to stay still to avoid collisions).
…________________________________
From: Alexander Makrigiorgos <[email protected]>
Sent: Tuesday, May 7, 2019 8:16:18 PM
To: PacktPublishing/Hands-On-Intelligent-Agents-with-OpenAI-Gym
Cc: Praveen Palanisamy; Comment
Subject: Re: [PacktPublishing/Hands-On-Intelligent-Agents-with-OpenAI-Gym] A2C agent doesn't act (#24)
That's true, but it is still loading the trained A2C_Carla-v0.ptm agent for the train mode correct? It has the same behaviour in test mode unfortunately =\ it simply sits there not taking any actions.
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub<#24 (comment)>, or mute the thread<https://github.com/notifications/unsubscribe-auth/ABEMVMVVD4LFX33ZVICMG5LPUILVFANCNFSM4HLGF3VQ>.
from hands-on-intelligent-agents-with-openai-gym.
praveen-palanisamy
commented on August 23, 2024
But, it is strange if you don't see the vehicle moving at all. It is supposed to be trying several actions and each will produce different trajectories of motion good or bad.
from hands-on-intelligent-agents-with-openai-gym.
Related Issues (20)
- How to do inference for Carla after training on OpenAI gym using Ray? HOT 1
- Deep Q-learning on Carla Env HOT 11
- Carla agent performance and training time HOT 4
- Have you tried to use DQN on the Carla environment? HOT 3
- wrapper for CARLA 0.9.x HOT 3
- Error connecting: (localhost:18872) failed to connect: [Errno 111] Connection refused, attempt 0 HOT 1
- Best episode reward didn't save HOT 6
- brew install boost-python --with-python3 does not work anymore HOT 2
- does carla_gym env work on windows? HOT 2
- ch7 error during reset HOT 3
- How to replace self._spec = lambda: None HOT 3
- ERROR: tcpserver 41826 : error writing message: Broken pipe HOT 8
- Continue to turn right when use non-discrete_actions HOT 5
- Change weather during the training HOT 2
- ModuleNotFoundError: No module named 'gym.envs.atari' still happening HOT 1
- TCP connection error in ch 7 HOT 3
- what is the version of all packages? HOT 1
- Sensors problem ch7
- input shape of carla-v0.ptm
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from hands-on-intelligent-agents-with-openai-gym.