Jonathan Balloch's repositories
sheeprl
Distributed Reinforcement Learning accelerated by Lightning Fabric
CBGM
An asynchronous fork of Concept Bottleneck Generative Models
LIBERO
Benchmarking Knowledge Transfer in Lifelong Robot Learning
dueling-obj-entropy-sampling
Efficient Online Adaptation of World Models with Dueling Objective Entropy Sampling
awesome-robotics-ai-companies
A living list of important industry innovators in the Robotics and AI space
cleanrl
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
tinygrad
You like pytorch? You like micrograd? You love tinygrad! ❤️
simpleaichat
Python package for easily interfacing with chat apps, with robust features and minimal code complexity.
rembg-webapp-tutorial
a simple webapp with rembg
rl-exploration-transfer
A fork of RLeXplore focused on studying the performance of exploration methods in online task transfer learning scenarios
PaperWM.spoon
Tiled scrollable window manager for MacOS
playingpretend
Imaginative Agents using Large Language Models to Plan Grand Adventures Grounded in the Real World
interconnects-tools
Python tools for easily translating your blog content to podcasts & YouTube
dm2gymnasium
For converting DeepMind environments to Farama Foundation Gymnasium format
continual_world
Continual World updated to mujoco and gymnasium
Metaworld
Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning
transfer-dreamer
Non-stationary and Novelty adapting RL with world models
Made-With-ML
Learn how to design, develop, deploy and iterate on production-grade ML applications.
dreamerv2
Mastering Atari with Discrete World Models
Launcher-Calculator
An open source orbital launch vehicle (rocket) payload calculator by Launcher
ultradreamer
Dreamerv3 + S5 + DenoisedMDP + RAC
AutoGPTProblemSolver
Custom AutoGPT agent
balloch.github.io
professional website
gpt-engineer
Specify what you want it to build, the AI asks for clarification, and then builds it.
generative_agents
Generative Agents: Interactive Simulacra of Human Behavior
wolverine
wolverine but trying to make it work with locally hosted llms
turret_bot
a robot turret for guarding my gardens and lawn against their greatest enemy...SQUIRRELS
cr-dv2
DreamerV2 implementation of Curious Replay, a method for prioritizing experience replay that is tailored to model-based reinforcement learning agents.