mcandocia / splendor_ai
a neural-network-based AI that learns to play Splendor
☆14Updated 6 years ago
Related projects ⓘ
Alternatives and complementary repositories for splendor_ai
- An implementation of 9x9 Tic Tac Toe☆77Updated 4 years ago
- UCThello - a board game demonstrator (Othello variant) with computer AI using Monte Carlo Tree Search (MCTS) with UCB (Upper Confidence B…☆25Updated last year
- The Path to Nash Equilibrium☆38Updated last year
- 2048 AI☆88Updated 7 years ago
- A JIT compiled chess engine which traverses the search tree in batches in a best-first manner, allowing for neural network batching, asyn…☆29Updated 2 years ago
- Game AI Game Engine☆98Updated 5 years ago
- An implementation of the AlphaZero algorithm for chess☆34Updated last year
- ☆40Updated 11 years ago
- Chess position evaluation using neural networks☆25Updated 4 years ago
- ☆9Updated 5 years ago
- Toolkit designed to ease development of your Deep Neural Network models for the game of Go (weiqi, baduk).☆20Updated 7 years ago
- Reinforcement learning algorithms to play Poker☆15Updated 2 years ago
- Code for paper "A simple algorithm for computing Nash-equilibria in incomplete information games"☆10Updated 7 years ago
- Implementation of the X-armed Bandits algorithm, as detailed in the paper, "X-armed Bandits", Bubeck et al., 2011.☆9Updated 6 years ago
- Learning from zero (mostly based off of AlphaZero) in General Game Playing.☆81Updated 2 years ago
- experimental chess engine based on temporal-difference reinforcement learning☆27Updated 8 years ago
- Go Game Move Variations Generator / Reviewer using Leela Engine☆15Updated 7 years ago
- A Neural Network designed to solve any rubik's cube of size NxNxN☆20Updated 9 years ago
- Connect4 reinforcement learning by AlphaGo Zero methods.☆114Updated 3 years ago
- using CNN to do move prediction and board evaluation for the board game Go☆145Updated 6 years ago
- Research code for solvers and models of the game of 2048☆53Updated last year
- Collection of game-theoretic algorithms for Poker☆29Updated 5 years ago
- Demo of UCT (MCTS) in Python / Numpy☆83Updated last year
- Sandbox for playing with neural nets for Go☆74Updated 5 years ago
- Poster for "A Neural Representation for Sketch Drawings" for ICLR 2018 Conference☆22Updated 6 years ago
- A library to implement counterfactual regret minimization on various abstract strategy games☆16Updated 5 years ago
- Simulation of Great filter concept in Fermi Paradox using RL, GA and Tensorflow.js☆29Updated 6 years ago
- Margin-dependent Elo ratings for the NFL☆14Updated 5 years ago