danijar / elements
Building blocks for productive research
☆51Updated last month
Alternatives and similar repositories for elements:
Users that are interested in elements are comparing it to the libraries listed below
- PyTorch Package For Quasimetric Learning☆41Updated 4 months ago
- General Modules for JAX☆64Updated 3 weeks ago
- GPT implementation in Flax☆18Updated 3 years ago
- Sandbox environment for generalizable agent research☆24Updated 2 years ago
- ☆44Updated last year
- Accelerated replay buffers in JAX☆41Updated 2 years ago
- ☆56Updated 2 years ago
- Codebase for "Uni[MASK]: Unified Inference in Sequential Decision Problems"☆54Updated 8 months ago
- Vectorization techniques for fast population-based training.☆55Updated 2 years ago
- Source code for the paper "Policy Architectures for Compositional Generalization in Control"☆30Updated 2 years ago
- ☆30Updated 4 years ago
- ☆43Updated 6 months ago
- Jax implementation of Proximal Policy Optimization (PPO) specifically tuned for Procgen, with benchmarked results and saved model weights…☆53Updated 2 years ago
- Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning (NeurIPS2021)☆20Updated 3 years ago
- Simplistic Pytorch Implementation of the Dreamer-RL☆21Updated 2 years ago
- Fast reinforcement learning research☆57Updated 3 months ago
- Docker containers of baseline agents for the Crafter environment☆28Updated 3 years ago
- Discovering and Achieving Goals via World Models, NeurIPS 2021☆85Updated last year
- Generalised UDRL☆37Updated 2 years ago
- Change-Based Exploration Transfer☆36Updated 2 years ago
- ☆42Updated 4 years ago
- ☆47Updated 2 years ago
- ☆31Updated last year
- CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRL☆109Updated 7 months ago
- Reinforcement Learning via Supervised Learning☆71Updated 2 years ago
- Learning Robust Dynamics Through Variational Sparse Gating☆21Updated 2 years ago
- Conservative Q learning in Jax☆53Updated 2 years ago
- Simplifying Model-based RL: Learning Representations, Latent-space Models and Policies with One Objective☆79Updated 2 years ago
- ☆27Updated last year
- [ICLR 22] Value Gradient weighted Model-Based Reinforcement Learning.☆24Updated last year