jjoller / aixi
Implementation of the Monte-Carlo CTW AIXI approximation as described by Joel Veness et al.
☆12Updated 8 years ago
Alternatives and similar repositories for aixi:
Users that are interested in aixi are comparing it to the libraries listed below
- MC-AIXI-CTW by Marcus Hutter and his students (in particular Daniel Visentin)☆49Updated 13 years ago
- Python implementation of tabular asynchronous actor critic☆11Updated 9 years ago
- Simple, small, fully-connected Python version of NeoRL☆11Updated 9 years ago
- An attempt to reimplement the 2013 paper by Wissner-Gross & Freer☆10Updated 4 months ago
- Implementation of https://medium.com/ai-control/alba-an-explicit-proposal-for-aligned-ai-17a55f60bbcf☆27Updated 7 years ago
- Generative Sparse Distributed Representations, a fast generative model written in Python (Original C++ implementation https://github.com/…☆24Updated 8 years ago
- Algorithmic Intelligence Quotient☆39Updated 3 years ago
- Code for the Neural GPU☆48Updated 9 years ago
- ☆43Updated 2 years ago
- Modeling agents with probabilistic programs☆67Updated 5 years ago
- ☆37Updated 8 years ago
- A Goal-Oriented Approach to Knowledge Discovery in Multi-Agent Systems☆41Updated 8 years ago
- Differentiable neural computers☆27Updated 8 years ago
- Code to reproduce the results in the "Unsupervised Learning of Goal Spaces for Intrinsically Motivated Exploration"☆21Updated 7 years ago
- ☆17Updated 8 years ago
- Differentiable Forth Interpreter☆70Updated 7 years ago
- ☆46Updated 11 years ago
- Code for a generative controller for the AI Gym cartpole task☆15Updated 8 years ago
- Implementations of differentiable stacks, queues, and deques from "Learning to Transduce with Unbounded Memory"☆20Updated 9 years ago
- AIXIjs - General Reinforcement Learning in the Browser☆147Updated 4 years ago
- A large collection of example and demo Soar agents for a variety of domains and problems.☆23Updated 7 years ago
- ☆43Updated 7 years ago
- RNN with differentiable structure (number of neurons)☆22Updated 8 years ago
- Differentiable Neural Computer implementation in Tensorflow☆35Updated 8 years ago
- A Python implementation of the gradient REBAR estimator.☆46Updated 6 years ago
- Neocortex-like reinforcement learning that runs on the GPU or CPU (OpenCL)☆69Updated 9 years ago
- Reference implementation of algorithms for reinforcement learning and Markov decision processes.☆12Updated 4 years ago
- Universal library for deep reinforcement learning.☆38Updated 9 years ago
- Replication of Uber Neuroevolution paper☆46Updated 7 years ago
- Asynchronous Advantage Actor Critic☆20Updated 8 years ago