camall3n Goto Github PK

actgen

Action Generalization

alcazar-gen

SAT-based generator for Alcazar puzzles

arena_3.0

atari-mac

Atari experiments for Mean Actor-Critic

atari-representation-learning

Code for "Unsupervised State Representation Learning in Atari"

bass

Script to generate crappy basslines

cchf

Cognitively constrained human feedback

compact_abstraction

DQN implementation in pytorch

curl

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

deep_abstract_q_network

deep_bisim4control

Learning Invariant Representations for Reinforcement Learning without Reconstruction

depq

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

dirichlet_viewer

Matlab visualizer for Dirichlet and Beta distributions

disent

🧶 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

dreamerv2

Mastering Atari with Discrete World Models

factored-reps

fd-scoping

The Fast Downward domain-independent classical planning system

firefox-ios

Firefox for iOS

focused-macros

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

grl

gym-miniworld

Simple 3D interior simulator for RL & robotics research

hrl

Robust deep skill chaining

iceberg

A compositional diagramming and animation library as an eDSL in Python

lab

A customisable 3D platform for agent-based AI research

markov-state-abstractions

Image-based gridworld experiment for learning Markov state abstractions

memristor-spice

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

onager

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

open_spiel

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

pddlgym

Convert a PDDL domain into an OpenAI Gym environment.

pfrl

PFRL: a PyTorch-based deep reinforcement learning library