Guillemdb / FractalAI
Celular automaton-based calculus for the masses
☆110Updated 4 years ago
Related projects: ⓘ
- ☆45Updated this week
- 2019 talk at GECCO☆68Updated 5 years ago
- Let's solve the flatland challenge!☆73Updated 11 months ago
- Mixture Density Networks (Bishop, 1994) tutorial in JAX☆57Updated 4 years ago
- Generic reinforcement learning codebase in TensorFlow☆95Updated 2 years ago
- Code for "Spinning Up a Pong AI With Deep RL" on FloydHub.☆54Updated 5 years ago
- ☆180Updated last month
- Cellular automaton-based calculus for the masses☆23Updated 6 years ago
- High performance implementation of Deep neuroevolution in pytorch using mpi4py. Intended for use on HPC clusters☆24Updated 2 years ago
- ☆77Updated this week
- Training neural networks to communicate with a visual language☆74Updated last year
- Train self-modifying neural networks with neuromodulated plasticity☆77Updated 4 years ago
- A library that makes Evolutionary Strategies (ES) simple to use.☆177Updated 3 years ago
- A set of 13 diverse machine-learning tasks that require memory to solve.☆221Updated 3 years ago
- Neural Turing Machines in pytorch☆46Updated 2 years ago
- ☆156Updated 4 years ago
- ☆48Updated 4 years ago
- An experiment with "freely" wired neural networks (no layers)☆163Updated last month
- [ICML-18] Codes for the custom games we built to compare RL agents with humans☆66Updated 5 years ago
- RLtime is a reinforcement learning library focused on state-of-the-art q-learning algorithms and features☆138Updated 4 years ago
- SafeLife: safety benchmarks for reinforcement learning agents☆59Updated 3 years ago
- EIGen: Evolutionary Illusion Generator, based on predictive coding.☆55Updated 6 months ago
- PyTorch implementations of recent optimization algorithms for deep learning.☆61Updated 4 years ago
- Functional machine learning for fun☆84Updated 3 years ago
- presentations☆44Updated 5 years ago
- ☆76Updated 4 years ago
- Open-source library for a reinforcement learning research.☆54Updated last year
- Reinforcement learning in TensorFlow 2☆22Updated 2 years ago
- ☆80Updated 11 months ago
- Adapting the AlphaZero algorithm to remove the need of execution traces to train NPI.☆77Updated 11 months ago