You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The goal of this issue is to release an agent that can interact and learn (and hopely win) from Joep's Bomberman.
Expected behaviour
Ideally develop an agent with an advanced reinforcement learning algorithm (like rainbow) that make the win really hard for a real player. But an agent that can finish the game without killing himself is already something I think.
Environment
OS and version
Proposed solution
Update the possible actions from the new env (it will change the output of the model)
Update the processing of the new env states (it will change the input of the model)
Make such modifications modular. Nothing hardcoded or not simple to adjust to any env.
The text was updated successfully, but these errors were encountered:
Description
The goal of this issue is to release an agent that can interact and learn (and hopely win) from Joep's Bomberman.
Expected behaviour
Ideally develop an agent with an advanced reinforcement learning algorithm (like rainbow) that make the win really hard for a real player. But an agent that can finish the game without killing himself is already something I think.
Environment
Proposed solution
The text was updated successfully, but these errors were encountered: