self-supervisor
(Augustine Mavor-Parker). PhD student at UCL Centre for Artificial Intelligence with Lewis Griffin and Caswell Barry.
University College LondonLondon
Pinned Repositories
Escaping-Stochastic-Traps-With-Aleatoric-Mapping-Agents
gruvbox-gantt-charts-with-pgfgantt
gym-minigrid_personal
Minimalistic gridworld package for OpenAI Gym
How_to_stay_curious_while_avoiding_noisy_TVs
jax
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
SARSA-Mountain-Car-Sutton-and-Barto
Implementation of Sutton and Barto SARSA mountain car algorithm, with their tile coding implementation used as features.
self-supervisor.github.io
A minimalist Jekyll theme, ideally designed for your academic site.
self-supervisor's Repositories
self-supervisor/How_to_stay_curious_while_avoiding_noisy_TVs
self-supervisor/Escaping-Stochastic-Traps-With-Aleatoric-Mapping-Agents
self-supervisor/gym-minigrid_personal
Minimalistic gridworld package for OpenAI Gym
self-supervisor/allocentric-scene-perception
This repo hosts both the Allocentric Scene Perception (ASP) benchmark and a biologically plausible model for unsupervised segmentation of objects
self-supervisor/cule
CuLE: A CUDA port of the Atari Learning Environment (ALE)
self-supervisor/gruvbox-gantt-charts-with-pgfgantt
self-supervisor/jax
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
self-supervisor/SARSA-Mountain-Car-Sutton-and-Barto
Implementation of Sutton and Barto SARSA mountain car algorithm, with their tile coding implementation used as features.
self-supervisor/self-supervisor.github.io
A minimalist Jekyll theme, ideally designed for your academic site.
self-supervisor/brax
Massively parallel rigidbody physics simulation on accelerator hardware.
self-supervisor/cleanrl
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
self-supervisor/genomic_bottleneck
self-supervisor/gymnax-blines
Baselines for gymnax 🤖
self-supervisor/implementations-nfq
Neural Fitted Q Iteration - First Experiences with a Data Efficient Neural Reinforcement Learning Method
self-supervisor/IsaacGymEnvs
Isaac Gym Reinforcement Learning Environments
self-supervisor/minihack
MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research
self-supervisor/noreward-rl
[ICML 2017] TensorFlow code for Curiosity-driven Exploration for Deep Reinforcement Learning
self-supervisor/purejaxrl
Really Fast End-to-End Jax RL Implementations
self-supervisor/python-rl
Some Reinforcement Learning in Python
self-supervisor/PyTorch-CIFAR-10-autoencoder
This is a reimplementation of the blog post "Building Autoencoders in Keras". Instead of using MNIST, this project uses CIFAR10.
self-supervisor/random-network-distillation
Code for the paper "Exploration by Random Network Distillation"
self-supervisor/ray
Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a toolkit of libraries (Ray AIR) for accelerating ML workloads.
self-supervisor/SR-Learning-Resources
Some notebooks and code to help people get started with understanding successor representations using both discrete states and continuous features
self-supervisor/streamlit-agent
Reference implementations of several LangChain agents as Streamlit apps
self-supervisor/subnetwork-probing
self-supervisor/vizdoomgym
OpenAI Gym wrapper for ViZDoom enviroments
self-supervisor/wandb_pickle
Wrapper around wandb that makes it easier to do custom python plots.
self-supervisor/wandb_scraper