Simple implementation of Wolfenstein 3D game using Raycasting Algorithm integrated with Proximal Policy Optimization ( PPO ) Deep Reinforcement Learning Technique.

1. Basic
2. Defend The Center
3. Deadly Corridor

1. Train ( Training The Model )
2. Test ( Testing The Model )

1. Easy → 1
2. Medium → 2
3. Hard → 3

Fig: Basic Level Episode Length & Reward Plot

Fig: Basic Level Loss Plot

Fig: Defend Level Episode Length & Reward Plot

Fig: Defend Level Loss Plot

Fig: Deadly Level Episode Length & Reward Plot

Fig: Deadly Level Loss Plot

python3 ./main.py --level { basic | defend } --train

python3 ./main.py --level { basic | defend } --test --steps { steps }

1. Easy
2. Medium
3. Hard

python3 ./main.py --level defend --train --skill { skill }

python3 ./main.py --level defend --train --skill { skill } --curr

python3 ./main.py --level defend --test --skill { skill } --steps { steps }

1. --level basic --train
2. --level basic --test --steps { steps }
3. --level defend --train
4. --level defend --test --steps { steps }
5. --level deadly --train --skill { skill }
6. --level deadly --train --skill { skill } --curr
7. --level deadly --test --skill { skill } --steps { steps }

python3 ./main.py --level basic --train

python3 ./main.py --level defend --test --steps 200000

python3 ./main.py --level deadly --train --skill 2

python3 ./main.py --level deadly --train --skill 3 --curr

python3 ./main.py --level deadly --test --skill 1 --steps 700000

Note: Curriculum Learning is only available if a model has been trained on the previous difficulty mode i.e. Curriculum Learning on Hard mode is only available if a model is available for Medium mode.