Vasileios Kochliaridis

I have have tested 3 times PPOClipAgent in LunarLander-v2 using the example https://github.com/tensorflow/agents/blob/master/tf_agents/examples/ppo/schulman17/ppo_clip_train_eval.py It is working fine. The agent learns & converges quickly. Then I added entropy regularization = 0.01,...

Well, I found a way around this.... I copied the `ActorDistributionNetwork `class and just passed the argument to the encoding network and it worked! However, it's such a shame that...

@sguada Hello, It does allow 1D convolutions. However, the `ActionDistributionNetwork ` class does not allow you to pass `CONV_TYPE_1D` to the parameter `"conv_type"` of the encoding network.

1. Can you verify that you downloaded file 'environment.carla_environment'" 2. Run the script from the main directory.

For some reason it cannot find environment folder. Once you download the repository, make sure all scripts run inside "code" folder, where environment folder is visible.

Well, the repository is kinda old, so I'd suggest check out the new one: https://github.com/kochlisGit/Noise-Adaptive-Driving-Assistance-System It is better and easier to train!

Hello, unfortunately no. But, we are releasing a newer version of the agent, easier to train and more effective within this week

Here is the new version: https://github.com/kochlisGit/Noise-Adaptive-Driving-Assistance-System

hello. Can you tell me the version of tensorflow as well as tf-addons?

I think there must be a version mismatch between tf 2.11 and tf-addons. Try older tf version.