-
Google DeepMind, University College London
- London
- rockt.github.io
- @_rockt
Highlights
- Pro
Stars
heiner / nle
Forked from facebookresearch/nleThe NetHack Learning Environment
Efficient baselines for autocurricula in JAX.
ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.
Official repo for the E3B algorithm described in the paper "Exploration via Elliptical Episodic Bonuses".
Nethack Learning Environment Wrapper for Language Interface
Accelerated Quality-Diversity
TeachMyAgent is a testbed platform for Automatic Curriculum Learning methods in Deep RL.
Publication-ready NN-architecture schematics.
👻 Use your text editor to write in your browser. Everything you type in the editor will be instantly updated in the browser (and vice versa).
A library for distributed ML training with PyTorch
MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research
Tiny Differentiable Simulator is a header-only C++ and CUDA physics library for reinforcement learning and robotics with zero dependencies.
functorch is JAX-like composable function transforms for PyTorch.
A platform for managing machine learning experiments
Benchmarking the Spectrum of Agent Capabilities
Dynamic Adversarial Benchmarking platform
High throughput synchronous and asynchronous reinforcement learning
A graphical frontend for exploring your org-roam Zettelkasten
A library of reinforcement learning components and agents
A small package to create visualizations of PyTorch execution graphs
Documentation: https://stratega.readthedocs.io/en/latest/
An interface with micropolis for city-building agents, packaged as an OpenAI gym environment
Unicode-based scientific plotting for working in the terminal