This is a custom stablebaselines3 bullet-hell environment. Agent uses DQN and PPO to learn how to dodge bullets. Created as part of Stanford's AA228. Final grade was 120/120.
Read the accompanying paper here:
| Name | Name | Last commit date | ||
|---|---|---|---|---|
This is a custom stablebaselines3 bullet-hell environment. Agent uses DQN and PPO to learn how to dodge bullets. Created as part of Stanford's AA228. Final grade was 120/120.
Read the accompanying paper here: