akolishchak / hard-attentionView external linksLinks
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
Sorting:
- Code for a generative controller for the AI Gym cartpole task☆15Feb 22, 2017Updated 8 years ago
- Active inference implementation of dynamic multi-armed bandits☆20Jun 25, 2025Updated 7 months ago
- Probabilistic inference for models of behaviour☆10Oct 13, 2025Updated 4 months ago
- General framework for Bayesian inversion of continuous hierarchical models☆10Sep 20, 2021Updated 4 years ago
- Implement BinaryNet of CNN with chainer☆11May 5, 2016Updated 9 years ago
- ☆14Oct 7, 2022Updated 3 years ago
- Model-Free Episodic Control☆14Jan 12, 2017Updated 9 years ago
- Gated Recurrent Unit with Low-rank matrix factorization☆34Mar 11, 2016Updated 9 years ago
- Repo for code for the NIPS paper entitled "An Architecture for Deep, Hierarchical Generative Models"☆14Oct 27, 2016Updated 9 years ago
- some RL algorithms☆19Dec 9, 2016Updated 9 years ago
- Deterministic Policy Gradient using torch7☆43Jun 2, 2016Updated 9 years ago
- Code for Continual Reinforcement Learning with Multi-Timescale Replay☆24Apr 16, 2020Updated 5 years ago
- ☆20Apr 27, 2016Updated 9 years ago
- ☆19Nov 2, 2016Updated 9 years ago
- Code for Attentive Recurrent Comparators☆58Mar 3, 2017Updated 8 years ago
- Input Inference for Control (i2c), a control-as-inference framework for optimal control☆25Sep 6, 2023Updated 2 years ago
- Highway networks implemented in PyTorch.☆54Apr 5, 2017Updated 8 years ago
- ☆27Jan 14, 2025Updated last year
- Torch implementation of Sequence to Sequence Learning with Neural Networks☆24Oct 14, 2015Updated 10 years ago
- ☆58Aug 28, 2018Updated 7 years ago
- ☆64Jun 2, 2017Updated 8 years ago
- ☆30Apr 15, 2017Updated 8 years ago
- A collection of machine learning datasets for use with Torch7.☆36Mar 12, 2014Updated 11 years ago
- ☆10Dec 21, 2022Updated 3 years ago
- Diffusion Probabilistic Model in Jax☆11Apr 20, 2024Updated last year
- Reinforcement Learning through Active Inference☆81Apr 27, 2020Updated 5 years ago
- The first public PyTorch implementation of Attentive Recurrent Comparators☆146Aug 31, 2017Updated 8 years ago
- Reinforcement learning models in ViZDoom environment☆130Mar 9, 2022Updated 3 years ago
- Docker image for Left 4 Dead 2 (L4D2) server.☆11Oct 5, 2020Updated 5 years ago
- reinforcement learning. policy gradient. PCL☆37Apr 25, 2017Updated 8 years ago
- ☆14Sep 29, 2025Updated 4 months ago
- KCP - A Fast and Reliable ARQ Protocol A KCP implementation in Erlang☆10Mar 15, 2019Updated 6 years ago
- Deep Generative Model (Torch)☆11Apr 19, 2016Updated 9 years ago
- A Tree-LSTM-based dependency tree sentiment labeler☆15May 9, 2019Updated 6 years ago
- ☆10May 5, 2017Updated 8 years ago
- 模拟键盘输入进行粘贴，用OCR识图进行文本复制☆11May 26, 2023Updated 2 years ago
- more composable than other neural network libraries☆42Aug 11, 2016Updated 9 years ago
- This is the implementation of paper Model Free Episodic Control☆36Sep 30, 2019Updated 6 years ago
- Provides and wraps the Randomkit library, copied from Numpy.☆34Apr 23, 2019Updated 6 years ago