Leaning hard attention model by policy gradient with rewards based on active inference.
☆22Sep 9, 2017Updated 8 years ago
Alternatives and similar repositories for hard-attention
Users that are interested in hard-attention are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Code for a generative controller for the AI Gym cartpole task☆15Feb 22, 2017Updated 9 years ago
- Active inference implementation of dynamic multi-armed bandits☆20Jun 25, 2025Updated 11 months ago
- Probabilistic inference for models of behaviour☆13Mar 5, 2026Updated 2 months ago
- General framework for Bayesian inversion of continuous hierarchical models☆10Sep 20, 2021Updated 4 years ago
- Gated Recurrent Unit with Low-rank matrix factorization☆35Mar 11, 2016Updated 10 years ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- Implement BinaryNet of CNN with chainer☆11May 5, 2016Updated 10 years ago
- Repo for code for the NIPS paper entitled "An Architecture for Deep, Hierarchical Generative Models"☆14Oct 27, 2016Updated 9 years ago
- Model-Free Episodic Control☆14Jan 12, 2017Updated 9 years ago
- ☆16Mar 10, 2018Updated 8 years ago
- Design good curriculums for deep reinforcement learning☆14May 18, 2016Updated 10 years ago
- Explore and Control with Adversarial Surprise☆10Jul 20, 2021Updated 4 years ago
- Code for Continual Reinforcement Learning with Multi-Timescale Replay☆24Apr 16, 2020Updated 6 years ago
- Deterministic Policy Gradient using torch7☆43Jun 2, 2016Updated 9 years ago
- PyOblige is Python wrapper for OBLIGE - random level generator for Doom☆11Jul 2, 2018Updated 7 years ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Deep Variational Information Bottleneck (DVIB) in PyTorch.☆10Apr 25, 2020Updated 6 years ago
- This package aims to make development with ML-Agents quicker and easier.☆10Oct 31, 2019Updated 6 years ago
- Temporal Regularization of Saliency Maps in Egocentric Videos☆10Apr 23, 2019Updated 7 years ago
- ☆20Apr 27, 2016Updated 10 years ago
- some RL algorithms☆19Dec 9, 2016Updated 9 years ago
- Pytorch Code for Semi-supervised Learning on MNIST Data Set☆12Mar 11, 2017Updated 9 years ago
- A docker container that lets you run AirSim without building it.☆14Sep 20, 2017Updated 8 years ago
- PyTorch implementation of different Deep RL algorithms for the LunarLander-v2 environment in OpenAI Gym☆11May 20, 2018Updated 8 years ago
- Input Inference for Control (i2c), a control-as-inference framework for optimal control☆26Sep 6, 2023Updated 2 years ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Reinforcement learning models in ViZDoom environment☆130Mar 9, 2022Updated 4 years ago
- ☆19Nov 2, 2016Updated 9 years ago
- Using a shared file to exchange data between Unity and Python☆13Oct 30, 2021Updated 4 years ago
- An opensource implementation of kanerva coding for use in reinforcement learning research☆11Mar 28, 2026Updated 2 months ago
- A lite version based on cyber RT☆15Feb 5, 2026Updated 3 months ago
- pytorch implementation of graph convolutions for semantic segmentation on ADE20K dataset☆16Oct 7, 2019Updated 6 years ago
- ☆10Nov 23, 2020Updated 5 years ago
- Official Pytorch Implementation of CMLO in the paper ”When to Update Your Model: Constrained Model-based Reinforcement Learning“☆10Nov 2, 2023Updated 2 years ago
- Cloud-and-Learning compatible Automated vehicle Platform (Mirrored from Gitlab, please post issues to the Gitlab link)☆11Apr 17, 2022Updated 4 years ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Torch implementation of Sequence to Sequence Learning with Neural Networks☆24Oct 14, 2015Updated 10 years ago
- Standalone utility to encrypt files with ice encryption, that doesn't depend on Steam.☆10Aug 28, 2013Updated 12 years ago
- Code for Attentive Recurrent Comparators☆56Mar 3, 2017Updated 9 years ago
- Reinforcement Learning through Active Inference☆83Apr 27, 2020Updated 6 years ago
- The first public PyTorch implementation of Attentive Recurrent Comparators☆145Aug 31, 2017Updated 8 years ago
- Highway networks implemented in PyTorch.☆54Apr 5, 2017Updated 9 years ago
- Slimebound character mod for Slay the Spire☆14Jun 30, 2020Updated 5 years ago