Always use a virtual environment to make sure package versions do not get mixed up. Use whichever environment you feel comfortable with, though it is recommended to use virtualenv. Also make sure your python interpreter is set to the correct python3 binary in your environment.
python3 -m venv .venv
pip install torch
pip install visdom
pip install gym==0.25.2
Run the command below and the pygame visualization should render as the model trains. Good luck!
python3 train.py --render --vis
Solving the car racing problem in OpenAI Gym using Proximal Policy Optimization (PPO). This problem has a real physical engine in the back end. You can achieve real racing actions in the environment, like drifting.
Every action will be repeated for 8 frames. To get velocity information, state is defined as adjacent 4 frames in shape (4, 96, 96). Use a two heads FCN to represent the actor and critic respectively. The actor outputs α, β for each actin as the parameters of Beta distribution.
Start a Visdom server with python -m visdom.server
, it will serve http://localhost:8097/ by default.
To train the agent, runpython train.py --render --vis
or python train.py --render
without visdom.
To test, run python test.py --render
.