danijar / portal
Fast and reliable distributed systems in Python
☆25Updated last month
Alternatives and similar repositories for portal:
Users that are interested in portal are comparing it to the libraries listed below
- Building blocks for productive research☆51Updated last month
- PyTorch Package For Quasimetric Learning☆41Updated 4 months ago
- GPT implementation in Flax☆18Updated 3 years ago
- General Modules for JAX☆64Updated 3 weeks ago
- Tools and Utils for Experiments (TUX)☆15Updated last month
- Bingham Policy Parameterization for 3D Rotations in Reinforcement Learning☆24Updated 3 years ago
- Accelerated replay buffers in JAX☆41Updated 2 years ago
- Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning (NeurIPS2021)☆20Updated 3 years ago
- PyTorch implementation for all methods and environments in the paper "MIMEx: Intrinsic Rewards from Masked Input Modeling"☆16Updated last year
- Fast reinforcement learning research☆57Updated 3 months ago
- Code for Continual Learning of Control Primitives☆18Updated 4 years ago
- Learning Robust Dynamics Through Variational Sparse Gating☆21Updated 2 years ago
- Standardized Minecraft Diamond Environment for Reinforcement Learning☆26Updated last year
- ☆81Updated 2 years ago
- code for CoRL 2020 paper "Contrastive Variational Model-Based Reinforcement Learning for Complex Observations"☆24Updated 3 years ago
- Differentiable Rasteriser implemented in JAX. Reference: https://github.com/erwincoumans/tinyrenderer, https://github.com/ssloy/tinyrende…☆71Updated last year
- An implementation of MuZero in JAX.☆56Updated 2 years ago
- Reinforcement Learning inside a 3D soccer simulation☆26Updated 6 months ago
- Model-Based Visual Planning with Self-Supervised Functional Distances (ICLR 2021)☆20Updated 3 years ago
- Standalone library of frequently-used wrappers for dm_env environments.☆17Updated 8 months ago
- Simplistic Pytorch Implementation of the Dreamer-RL☆21Updated 2 years ago
- ☆33Updated 3 years ago
- Discovering and Achieving Goals via World Models, NeurIPS 2021☆85Updated last year
- flexible meta-learning in jax☆12Updated last year
- Source code for the paper "Policy Architectures for Compositional Generalization in Control"☆30Updated 2 years ago
- ☆42Updated 2 years ago
- JAX implementation of VQVAE/VQGAN autoencoders (+FSQ)☆26Updated 9 months ago
- ☆30Updated last year
- a starter-kit for jaynes, the cloud-agnostic launch library☆17Updated 7 months ago
- Clockwork VAEs in JAX/Flax☆32Updated 3 years ago