Code for the paper "Skynet: A Top Deep RL Agent in the Inaugural Pommerman Team Competition"
-
Updated
May 9, 2019 - Python
Code for the paper "Skynet: A Top Deep RL Agent in the Inaugural Pommerman Team Competition"
A reinforcement learning project on micro in StarCraft II
Pommerman - A Bomberman reinforcement learning challenge in PyTorch 💣
Some implementations of agents in Pommerman
Learning-based MCTS in the Pommerman Environment
A Pommerman agent which simulates agents' ammo, kick ability, and other information
Unorganized code I wrote for training my Pommerman agents.
University courserwork to implement and improve AI techniques used in games (Bomberman). Techniques include Monte Carlo Tree Search, Evolutionary computation etc.,
Monte Carlo Tree Search with Progressive Bias and Decaying Reward for the Pommerman (Java version) game.
My Docker agent submission to the NeurIPS 2019 Pommerman challenge.
A place to experiment with various reinforcement learning approaches in the Pommerman environment.
Pommerman implementation with Imitation Learning, Actor-Critic Networks, Monte-Carlo-Tree-Search (MCTS), Action-Filter and Jitter-Correction
Modified the Monte Carlo Tree Search algorithm by introducing progressive bias to refine the selection process on Pommerman game setup.
Add a description, image, and links to the pommerman topic page so that developers can more easily learn about it.
To associate your repository with the pommerman topic, visit your repo's landing page and select "manage topics."