Loading repository data…
masouduut94 / repository
MCTS-agent-python
Monte Carlo Tree Search (MCTS) is a method for finding optimal decisions in a given domain by taking random samples in the decision space and building a search tree accordingly. It has already had a profound impact on Artificial Intelligence (AI) approaches for domains that can be represented as trees of sequential decisions, particularly games and planning problems. In this project I used a board game called "HEX" as a platform to test different simulation strategies in MCTS field.
#decision-space#game-of-hex#markov-decision-processes#mcts#monte-carlo-tree-search#reinforcement-learning
Live repository statistics
★ 71Stars
⑂ 10Forks
◯ 2Open issues
◉ 71Watchers
54/100
OPENREPOHUB HEALTH SIGNAL
Mixed signals
A transparent discovery signal based on current public GitHub metadata.
Recent activity35% weight
30
Community adoption25% weight
34
Maintenance state20% weight
85
License clarity10% weight
100
Project information10% weight
75
This score does not audit code, security, maintainers, documentation quality, or suitability. Verify the repository and its current documentation before adoption.
README preview
HexPy
Monte Carlo Tree Search Agent for the game of HEX
Demo:
Description
This code belongs to this paper :link: IMPROVING MONTE CARLO TREE SEARCH BY COMBINING RAVE AND QUALITY-BASED REWARDS ALGORITHMS.
what is Monte Carlo Tree Search(MCTS)?
MONTE Carlo Tree Search (MCTS) is a method for finding optimal decisions in a given domain by taking random samples in the decision space and building a search tree according to the results. It has already had a profound impact on Artificial Intelligence (AI) approaches for domains that can be represented as trees of sequential decisions, particularly games and planning problems. In this project I used different simulation strategies to enhance the agent policy to explore the environment.
from :link: A Survey of Monte Carlo Tree Search Methods
About contribution
Before you go through the details, I recommend you to get familiar with the framework reading these medium articles:
- A simple no math included introduction to reinforcement learning
- A simple introduction to Monte Carlo Tree Search
- Details of MCTS implementation on game of HEX
So if you are familiar with the whole concept of MCTS and UCT algorithm, you must know that in practice it suffers from sparse rewards. it takes so much time to warm up the tree with simple UCT algorithm. So in this case we first implemented the RAVE algorithm that helps warm up tree faster. then implemented several simulation strategy like Last Good Reply, PoolRAVE, Decisive Move and also UCB1-Tuned.
Then we applied quality based rewards in Quality-based Rewards for Monte-Carlo Tree Search Simulations which basically it asserts that we can apply discounted rewards by for each player (In some games, the game ends after limited number of moves. because there is no more movements).