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
- Chess position evaluation using neural networks☆25Updated 4 years ago
- An implementation of the AlphaZero algorithm for chess☆34Updated last year
- Deep learning chess engine, that has no idea about chess rules, but watches and learns☆17Updated 7 years ago
- An implementation of 9x9 Tic Tac Toe☆77Updated 4 years ago
- A reimplementation of the Google AlphaZero algorithm.☆18Updated 4 years ago
- ☆30Updated 6 years ago
- Sample code for generative recurrent autoencoders.☆25Updated 8 years ago
- UCThello - a board game demonstrator (Othello variant) with computer AI using Monte Carlo Tree Search (MCTS) with UCB (Upper Confidence B…☆26Updated last year
- Convert sc2 environment to gym-atari and play some mini-games☆21Updated 7 years ago
- AI for the game Uno☆19Updated 5 years ago
- Playing Board Game Splendor with Deep Reinforcement Learning☆33Updated 5 years ago
- Framework for writing bots that play Hanabi.☆36Updated 5 years ago
- Source code of the MaastCTS2 agent for General Video Game playing. Champion of the 2016 GVG-AI Single-Player Track, and runner-up of the …☆14Updated 3 years ago
- Tensorflow Implementation of Programmable Agents☆36Updated 7 years ago
- learning to play atari games with reinforcement learning☆10Updated 8 years ago
- The Path to Nash Equilibrium☆38Updated last year
- A simple moving dot environment for OpenAI Gym to test reinforcement learning algorithms☆22Updated 2 years ago
- Learning from zero (mostly based off of AlphaZero) in General Game Playing.☆82Updated last year
- Style transfer for chess.☆31Updated 7 years ago
- ☆29Updated 6 years ago
- A TensorFlow implementation of "DeepChess: End-to-End Deep Neural Network for Automatic Learning in Chess"☆87Updated 6 years ago
- ☆26Updated 4 years ago
- Connect4 reinforcement learning by AlphaGo Zero methods.☆114Updated 3 years ago
- ☆39Updated 7 years ago
- ☆57Updated last year
- Hex board game AI with self-play learning based on the AlphaZero algorithm☆31Updated 4 years ago
- Amazon access control challenge☆25Updated 10 years ago
- Conditional Associative Logic Memory☆27Updated 7 years ago