This is the Linux app named RLax whose latest release can be downloaded as RLax0.1.8sourcecode.tar.gz. It can be run online in the free hosting provider OnWorks for workstations.
Download and run online this app named RLax with OnWorks for free.
Urmați aceste instrucțiuni pentru a rula această aplicație:
- 1. Ați descărcat această aplicație pe computer.
- 2. Introduceți în managerul nostru de fișiere https://www.onworks.net/myfiles.php?username=XXXXX cu numele de utilizator pe care îl doriți.
- 3. Încărcați această aplicație într-un astfel de manager de fișiere.
- 4. Porniți emulatorul online OnWorks Linux sau Windows online sau emulatorul online MACOS de pe acest site web.
- 5. Din sistemul de operare OnWorks Linux pe care tocmai l-ați pornit, accesați managerul nostru de fișiere https://www.onworks.net/myfiles.php?username=XXXXX cu numele de utilizator dorit.
- 6. Descărcați aplicația, instalați-o și rulați-o.
CAPTURĂ DE ECRAN:
RLax
DESCRIERE:
RLax (pronounced “relax”) is a JAX-based library developed by Google DeepMind that provides reusable mathematical building blocks for constructing reinforcement learning (RL) agents. Rather than implementing full algorithms, RLax focuses on the core functional operations that underpin RL methods—such as computing value functions, returns, policy gradients, and loss terms—allowing researchers to flexibly assemble their own agents. It supports both on-policy and off-policy learning, as well as value-based, policy-based, and model-based approaches. RLax is fully JIT-compilable with JAX, enabling high-performance execution across CPU, GPU, and TPU backends. The library implements tools for Bellman equations, return distributions, general value functions, and policy optimization in both continuous and discrete action spaces. It integrates seamlessly with DeepMind’s Haiku (for neural network definition) and Optax (for optimization), making it a key component in modular RL pipelines.
Categorii
- Modular reinforcement learning primitives (values, returns, and policies)
- JAX-optimized for GPU/TPU acceleration and automatic differentiation
- Supports on-policy and off-policy learning paradigms
- Implements distributional value functions and general value functions
- Integrates with Haiku and Optax for neural network and optimization pipelines
- Comprehensive testing and examples for reproducibility and educational use
Limbaj de programare
Python, Unix Shell
Categorii
This is an application that can also be fetched from https://sourceforge.net/projects/rlax.mirror/. It has been hosted in OnWorks in order to be run online in an easiest way from one of our free Operative Systems.