facebookresearch / phyre
PHYRE is a benchmark for physical reasoning.
☆430Updated last year
Related projects: ⓘ
- lagom: A PyTorch infrastructure for rapid prototyping of reinforcement learning algorithms.☆373Updated last year
- Multi-object image datasets with ground-truth segmentation masks and generative factors.☆254Updated 2 years ago
- Code for the paper "OpenAI Remote Rendering Backend"☆241Updated last year
- Repository for the paper "Planning to Explore via Self-Supervised World Models"☆213Updated last year
- Generative Query Network (GQN) in PyTorch as described in "Neural Scene Representation and Rendering"☆322Updated 5 years ago
- Velocity in deep-learning research☆276Updated last year
- Code for the paper "Quantifying Transfer in Reinforcement Learning"☆389Updated 11 months ago
- Open-Source Distributed Reinforcement Learning Framework by Stanford Vision and Learning Lab☆483Updated 4 years ago
- Dream to Control: Learning Behaviors by Latent Imagination☆599Updated 4 years ago
- Code for "Unsupervised State Representation Learning in Atari"☆239Updated 10 months ago
- DrQ: Data regularized Q☆401Updated last year
- RAD: Reinforcement Learning with Augmented Data☆400Updated 3 years ago
- A set of 13 diverse machine-learning tasks that require memory to solve.☆221Updated 3 years ago
- Spriteworld: a flexible, configurable python-based reinforcement learning environment☆368Updated 4 years ago
- A PyTorch Platform for Distributed RL☆737Updated 3 years ago
- ☆180Updated last month
- Code for the paper "Evolved Policy Gradients"☆251Updated 5 years ago
- BabyAI platform. A testbed for training agents to understand and execute language commands.☆688Updated 11 months ago
- Train embodied agents that can answer questions in environments☆294Updated last year
- Deep Planning Network: Control from pixels by latent planning with learned dynamics☆359Updated 2 years ago
- Implementation of Model-Agnostic Meta-Learning (MAML) in Jax☆188Updated last year
- We provide a pre-trained model for unconditional 19-step generation of CelebA-HQ images☆326Updated 4 years ago
- Dataset to assess the disentanglement properties of unsupervised learning methods☆477Updated 3 years ago
- Contrastive Learning of Structured World Models☆386Updated 4 years ago
- A PyTorch Library for Reinforcement Learning Research☆196Updated last year
- A colab that implements the Symplectic Gradient Adjustment optimizer from "The mechanics of n-player differentiable games"☆152Updated 5 years ago
- Paired Open-Ended Trailblazer (POET) and Enhanced POET☆240Updated 2 years ago
- ICLR Reproducibility Challenge 2019☆219Updated 5 years ago
- Differentiable Neural Computers, Sparse Access Memory and Sparse Differentiable Neural Computers, for Pytorch☆332Updated last month
- Datasets used to train Generative Query Networks (GQNs) in the ‘Neural Scene Representation and Rendering’ paper.☆274Updated 2 years ago