hr0nix / dejaxLinks
Accelerated replay buffers in JAX
β43Updated 3 years ago
Alternatives and similar repositories for dejax
Users that are interested in dejax are comparing it to the libraries listed below
Sorting:
- Baselines for gymnax π€β71Updated 2 years ago
- Vectorization techniques for fast population-based training.β56Updated 3 years ago
- General Modules for JAXβ67Updated 3 weeks ago
- JAX implementations of core Deep RL algorithmsβ82Updated 3 years ago
- An implementation of MuZero in JAX.β57Updated 2 years ago
- CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRLβ115Updated last year
- β83Updated 3 weeks ago
- Jax implementation of Proximal Policy Optimization (PPO) specifically tuned for Procgen, with benchmarked results and saved model weightsβ¦β58Updated 3 years ago
- πͺ The Sebulba architecture to scale reinforcement learning on Cloud TPUs in JAXβ59Updated last year
- Docker containers of baseline agents for the Crafter environmentβ28Updated 3 years ago
- Jax-Baseline is a Reinforcement Learning implementation using JAX and Flax/Haiku libraries, mirroring the functionality of Stable-Baselinβ¦β58Updated last week
- β84Updated 11 months ago
- A collection of RL algorithms written in JAX.β104Updated 3 years ago
- Contains JAX implementation of algorithms for inverse reinforcement learningβ72Updated last year
- Single-file SAC-N implementation on jax with flax and equinox. 10x faster than pytorchβ52Updated 2 years ago
- Accelerated minigrid environments with JAXβ149Updated last month
- β45Updated last year
- Corax: Core RL in JAXβ38Updated last year
- flexible meta-learning in jaxβ14Updated last year
- An Open-Ended Agentic Simulatorβ52Updated last year
- Building blocks for productive researchβ61Updated 2 months ago
- Dreamer on JAXβ16Updated 3 years ago
- Standard interface for entity based reinforcement learning environments.β38Updated last year
- Simple single-file baselines for Q-Learning in pure-GPU settingβ184Updated 6 months ago
- β19Updated 2 years ago
- Benchmarking RL for POMDPs in Pure JAX [Code for "Structured State Space Models for In-Context Reinforcement Learning" (NeurIPS 2023)]β110Updated last year
- Flax Implementation of DreamerV3 on Crafterβ16Updated 7 months ago
- Mitigating Partial Observability in Sequential Decision Processes via the Lambda Discrepancyβ20Updated 11 months ago
- Simple JAX Graphics Library.β36Updated 11 months ago
- β48Updated 2 years ago