Abstract

Video games have increasingly been used as AI benchmarks. In contrast to classic board games, video games require more frequent decision making, often in real-time settings, and additionally define more complex state spaces. They may also have some combination of hidden information, stochasticity, complex interaction rules, and large branching factors. Modern video game-based AI benchmarks do not provide agents with processed representations of the environment. The agents have to act based on the raw pixels, i.

Environment: Linux: Ubuntu 16.04 Python: 3.6.8 Step 1 Create a conda virtual environment with your virtual environment name(e.g. venv_dopamine) conda create -n venv_dopamine python=3.6.8 anaconda Step 2 Activate the virtual environment conda activate venv_dopamine Step 3 Move to the virtual environment directory cd venv_dopamine Step 4 Install the Obstacle Tower Environment git clone https://github.com/Unity-Technologies/obstacle-tower-env Step 5 cd obstacle-tower-env pip install ./ cd ..