Cam Allen

Image-based gridworld experiment for learning Markov state abstractions

Efficient Black-Box Planning Using Macro-Actions with Focused Effects

Simplifying Planning Tasks with Fact-Level Relevance Analysis

RL environments for quickly running image-based grid-world experiments

Lightweight python library for launching experiments and tuning hyperparameters, either locally or on a cluster

Lightweight python library for achieving deterministic random seeds

Circuit simulator based on Berkeley SPICE 3f5, with modifications to support memristors natively

No description.

No description.

🧶 Modular VAE disentanglement framework for python built with PyTorch Lightning ▸ Including metrics and datasets ▸ With strongly supervised, weakly supervised and unsupervised methods ▸ Easily configured and run with Hydra config ▸ Inspired by disentanglement_lib

Efficient Black-Box Planning Using Macro-Actions with Focused Effects

Atari experiments for Mean Actor-Critic

Concept filtering

⏰ AI conference deadline countdowns

Python implementation of 4D pinball domain

No description.

A compositional diagramming and animation library as an eDSL in Python

A highly-customisable gridworld game engine with some batteries included. Make your own gridworld games to test reinforcement learning agents!

Cognitively constrained human feedback

No description.

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

Action Generalization

Mastering Atari with Discrete World Models

Script to generate crappy basslines

A simple timer for profiling python code

A CUDA implementation of SIFT for NVidia GPUs

Robust deep skill chaining

No description.

RAD: Reinforcement Learning with Augmented Data

Firefox for iOS

No description.

PFRL: a PyTorch-based deep reinforcement learning library

Learning Invariant Representations for Reinforcement Learning without Reconstruction

CURL: Contrastive Unsupervised Representation Learning for Sample-Efficient Reinforcement Learning

PyTorch implementation of Soft Actor-Critic (SAC)

DQN implementation in pytorch

Simple 3D interior simulator for RL & robotics research

Convert a PDDL domain into an OpenAI Gym environment.

A customisable 3D platform for agent-based AI research

A min-max heap implementation for a double ended priority queue

Code for "Unsupervised State Representation Learning in Atari"

Rainbow: Combining Improvements in Deep Reinforcement Learning

A simple framework for experimenting with Reinforcement Learning in Python.

SAT-based generator for Alcazar puzzles

Tetris clone

No description.

Matlab visualizer for Dirichlet and Beta distributions