tansey / rl-tictactoeLinks
A reinforcement learning agent for tic-tac-toe. Implements the example from Chapter 1 of Sutton and Barto.
☆50Updated 7 years ago
Alternatives and similar repositories for rl-tictactoe
Users that are interested in rl-tictactoe are comparing it to the libraries listed below
Sorting:
- Machine learning and data science blog.☆69Updated last year
- Generative Adversarial Network Demo for Fresh Machine Learning #2☆73Updated 7 years ago
- Tutorial for Visual Turing Test (visual question answering, image question answering).☆118Updated 8 years ago
- Montréal Deep Learning Summer School 2016 material☆100Updated 9 years ago
- Python cognitive modelling suite☆100Updated 7 years ago
- ☆107Updated 7 years ago
- Repository for practical assignments for UvA Deep Learning Course 2016☆51Updated 7 years ago
- ☆88Updated 8 years ago
- Informal IPython experiments and tutorials. TensorFlow, machine learning/deep learning/RL, NLP applications.☆148Updated 8 years ago
- Testbed for deep reinforcement learning☆160Updated 8 years ago
- ☆114Updated last year
- my solutions for oxford's "deep nlp 2017" practical assignments☆65Updated 8 years ago
- random search, hill climbing, policy gradient☆145Updated 6 years ago
- Generative Adversarial Networks in Keras☆46Updated 4 years ago
- A curated list of awesome hyperparameters for deep learning☆78Updated 7 years ago
- things I help(ed) to build☆54Updated 3 months ago
- Generative Adversarial Networks with Keras☆156Updated 4 years ago
- Reasonably-okay-performing implementation of a GAN and an adversarial autoencoder on MNIST.☆29Updated 9 years ago
- Tutorial teaching the basics of Keras and some deep learning concepts☆104Updated 8 years ago
- ☆137Updated 8 years ago
- Language modellling using RNNs☆54Updated 7 years ago
- Playing Atari games with TensorFlow implementation of Asynchronous Deep Q-Learning☆42Updated 7 years ago
- Save keras weight matrices as short animated videos during training☆105Updated 8 years ago
- An implementation of the Neural Turing Machine as a keras recurrent layer.☆139Updated 8 years ago
- repository for the Variational Autoencoder (VAE) blogpost series from Fast Forward Labs☆103Updated 8 years ago
- customize this building block to make all the residual connections you can dream of☆80Updated 9 years ago
- ☆24Updated 9 years ago
- tensorflow reinforcement learning agents for OpenAI gym environments☆117Updated 8 years ago
- Reinforcement Learning with Goals☆170Updated 5 years ago
- DrMAD☆107Updated 7 years ago