mila-iqia / babyaiLinks
BabyAI platform. A testbed for training agents to understand and execute language commands.
☆750Updated 2 years ago
Alternatives and similar repositories for babyai
Users that are interested in babyai are comparing it to the libraries listed below
Sorting:
- Reimplementation of World-Models (Ha and Schmidhuber 2018) in pytorch☆649Updated 3 years ago
- World Models Experiments☆674Updated 3 years ago
- Code for the paper "Quantifying Transfer in Reinforcement Learning"☆405Updated 2 years ago
- Code for the paper "Large-Scale Study of Curiosity-Driven Learning"☆830Updated 4 years ago
- A PyTorch Platform for Distributed RL☆752Updated 4 years ago
- Spriteworld: a flexible, configurable python-based reinforcement learning environment☆372Updated 5 years ago
- Simple and easily configurable 3D FPS-game-like environments for reinforcement learning☆751Updated 3 weeks ago
- Code for Go-Explore: a New Approach for Hard-Exploration Problems☆579Updated 3 years ago
- RL starter files in order to immediately train, visualize and evaluate an agent without writing any line of code☆710Updated last year
- We release dataset collected for our research, code that implement neural network models described in the paper, and scripts to reproduce…☆162Updated 4 years ago
- A highly-customisable gridworld game engine with some batteries included. Make your own gridworld games to test reinforcement learning ag…☆661Updated 6 years ago
- PlayGround: AI Research into Multi-Agent Learning.☆778Updated 2 years ago
- EGG: Emergence of lanGuage in Games☆315Updated 8 months ago
- Dream to Control: Learning Behaviors by Latent Imagination☆698Updated 5 years ago
- Learning Latent Dynamics for Planning from Pixels☆1,227Updated 2 years ago
- Code for the paper "Exploration by Random Network Distillation"☆927Updated 5 years ago
- Reproduction of OpenAI and DeepMind's "Deep Reinforcement Learning from Human Preferences"☆333Updated 4 years ago
- RAD: Reinforcement Learning with Augmented Data☆416Updated 4 years ago
- hanabi_learning_environment is a research platform for Hanabi experiments.☆661Updated 2 years ago
- For educational materials related to the spinning up workshops.☆205Updated 6 years ago
- A TensorFlow implementation of Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures.☆1,015Updated 6 years ago
- bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent☆1,529Updated last year
- Code for "Unsupervised State Representation Learning in Atari"☆255Updated 2 years ago
- PHYRE is a benchmark for physical reasoning.☆457Updated 2 years ago
- Tensorflow/Keras code and trained models for Episodic Curiosity Through Reachability☆206Updated 5 years ago
- Code repository for the Animal AI Olympics competition☆576Updated 3 years ago
- Deep Planning Network: Control from pixels by latent planning with learned dynamics☆373Updated 4 years ago
- Dream to Control: Learning Behaviors by Latent Imagination☆576Updated 4 years ago
- Sokoban environment for OpenAI Gym☆390Updated 2 years ago
- Simple and easily configurable grid world environments for reinforcement learning☆2,380Updated 3 weeks ago