search

PacktPublishing / Hands-On-Intelligent-Agents-with-OpenAI-Gym

Code for Hands On Intelligent Agents with OpenAI Gym book to get started and learn to build deep reinforcement learning agents using PyTorch
https://www.packtpub.com/big-data-and-business-intelligence/hands-intelligent-agents-openai-gym
MIT License
366 stars 149 forks source link

How to do inference for Carla after training on OpenAI gym using Ray? #22

Closed Deepak3994 closed 5 years ago

Deepak3994 commented 5 years ago

Hi,

I have trained for A3C algorithm on Carla using Gym environment. May i know like at what point of time the models get dumped and also how to do the inference on the same for Carla.

praveen-palanisamy commented 5 years ago

Hi @Deepak3994 :

Models are automatically saved as the performance (best_reward attained) improves. You can change how frequently an improved model is saved by adjusting this config param:

https://github.com/PacktPublishing/Hands-On-Intelligent-Agents-with-OpenAI-Gym/blob/8a334e0d11e12654ddf1418f54738e8338137c9e/ch8/async_a2c_parameters.json#L13

If you are using the asyn_a2c_agent.py script, you can use the --test command-line argument to "do the inference".