mila-iqia / babyaiLinks
BabyAI platform. A testbed for training agents to understand and execute language commands.
☆744Updated last year
Alternatives and similar repositories for babyai
Users that are interested in babyai are comparing it to the libraries listed below
Sorting:
- World Models Experiments☆659Updated 3 years ago
- Reimplementation of World-Models (Ha and Schmidhuber 2018) in pytorch☆637Updated 3 years ago
- Spriteworld: a flexible, configurable python-based reinforcement learning environment☆372Updated 5 years ago
- Code for the paper "Quantifying Transfer in Reinforcement Learning"☆401Updated last year
- Code for the paper "Large-Scale Study of Curiosity-Driven Learning"☆822Updated 4 years ago
- A PyTorch Platform for Distributed RL☆750Updated 4 years ago
- Code for Go-Explore: a New Approach for Hard-Exploration Problems☆574Updated 2 years ago
- Dream to Control: Learning Behaviors by Latent Imagination☆661Updated 5 years ago
- For educational materials related to the spinning up workshops.☆203Updated 6 years ago
- RL starter files in order to immediately train, visualize and evaluate an agent without writing any line of code☆702Updated last year
- PlayGround: AI Research into Multi-Agent Learning.☆774Updated last year
- EGG: Emergence of lanGuage in Games☆307Updated 4 months ago
- We release dataset collected for our research, code that implement neural network models described in the paper, and scripts to reproduce…☆161Updated 4 years ago
- A highly-customisable gridworld game engine with some batteries included. Make your own gridworld games to test reinforcement learning ag…☆662Updated 6 years ago
- Code for the paper "Exploration by Random Network Distillation"☆909Updated 4 years ago
- Reproduction of OpenAI and DeepMind's "Deep Reinforcement Learning from Human Preferences"☆327Updated 3 years ago
- PHYRE is a benchmark for physical reasoning.☆449Updated 2 years ago
- Code repository for the Animal AI Olympics competition☆577Updated 3 years ago
- Simple and easily configurable 3D FPS-game-like environments for reinforcement learning☆741Updated last week
- bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent☆1,526Updated last year
- Code for "Unsupervised State Representation Learning in Atari"☆252Updated last year
- RAD: Reinforcement Learning with Augmented Data☆411Updated 4 years ago
- Sokoban environment for OpenAI Gym☆380Updated last year
- This will contain my notes for research papers that I read.☆619Updated 6 years ago
- hanabi_learning_environment is a research platform for Hanabi experiments.☆654Updated 2 years ago
- Simple and easily configurable grid world environments for reinforcement learning☆2,323Updated last week
- Tensorflow/Keras code and trained models for Episodic Curiosity Through Reachability☆205Updated 4 years ago
- A Python interface for reinforcement learning environments☆377Updated 2 years ago
- Learning Latent Dynamics for Planning from Pixels☆1,207Updated 2 years ago
- A collection of 100+ pre-trained RL agents using Stable Baselines, training and hyperparameter optimization included.☆1,182Updated 2 years ago