awesome-repositories.com
Blog
MCP
awesome-repositories.com

Descoperă cele mai bune repository-uri open source cu căutare AI.

ExploreazăCăutări recomandateAlternative open-sourceSoftware self-hostedBlogHartă site
ProiectDespreCum realizăm clasamentulPresăServer MCP
LegalConfidențialitateTermeni
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·
rail-berkeley avatar

rail-berkeley/d4rl

0
View on GitHub↗
1,693 stele·307 fork-uri·Python·Apache-2.0·7 vizualizări

D4rl

D4RL is an open-source benchmark for offline reinforcement learning. It provides standardized environments and datasets for training and benchmarking algorithms. A supplementary whitepaper and website are also available.

Features

  • Datasets and Benchmarks - Standardizes datasets for deep data-driven reinforcement learning research.
  • Reinforcement Learning Environments - Datasets and environments for offline reinforcement learning benchmarking.
  • World Models - Standardized datasets and environments for offline reinforcement learning.
  • Environment Benchmarks - Provides datasets and environments for offline reinforcement learning benchmarking.

Istoric stele

Graficul istoricului de stele pentru rail-berkeley/d4rlGraficul istoricului de stele pentru rail-berkeley/d4rl

Căutare AI

Explorează mai multe repository-uri excelente

Descrie ce ai nevoie în limbaj simplu — AI-ul sortează mii de proiecte open source selectate în funcție de relevanță.

Start searching with AI

Alternative open-source pentru D4rl

Proiecte open-source similare, clasificate după numărul de funcționalități comune cu D4rl.
  • openai/mujoco-pyO

    openai/mujoco-py

    0Vezi pe GitHub↗

    MuJoCo is a physics engine which can do very detailed efficient simulations with contacts. This library lets you use MuJoCo from Python.

    Vezi pe GitHub↗0
  • aravindr93/mjrlA

    aravindr93/mjrl

    0Vezi pe GitHub↗

    This package contains implementations of various RL algorithms for continuous control tasks simulated with MuJoCo.

    Vezi pe GitHub↗0
  • danijar/crafterAvatar danijar

    danijar/crafter

    566Vezi pe GitHub↗

    Status: Stable release

    Python
    Vezi pe GitHub↗566
  • deepmind/deepmind-researchAvatar deepmind

    deepmind/deepmind-research

    15,024Vezi pe GitHub↗

    This project is an AI research implementation library and machine learning research repository. It provides a collection of reference code, illustrative implementations, and open-source research datasets used to verify hypotheses and build upon existing models in artificial intelligence. The repository focuses on scientific research reproduction by translating theoretical findings from published papers into executable code. It includes specialized scientific simulation environments designed to test the behavior of autonomous agents and models within controlled settings. The project covers AI

    Jupyter Notebook
    Vezi pe GitHub↗15,024
Vezi toate cele 30 alternative pentru D4rl→

Întrebări frecvente

Ce face rail-berkeley/d4rl?

D4RL is an open-source benchmark for offline reinforcement learning. It provides standardized environments and datasets for training and benchmarking algorithms. A supplementary whitepaper and website are also available.

Care sunt principalele funcționalități ale rail-berkeley/d4rl?

Principalele funcționalități ale rail-berkeley/d4rl sunt: Datasets and Benchmarks, Reinforcement Learning Environments, World Models, Environment Benchmarks.

Care sunt câteva alternative open-source pentru rail-berkeley/d4rl?

Alternativele open-source pentru rail-berkeley/d4rl includ: openai/mujoco-py — MuJoCo is a physics engine which can do very detailed efficient simulations with contacts. This library lets you use… maximecb/gym-minigrid — Simple and easily configurable grid world environments for reinforcement learning. danijar/crafter — Status: Stable release. deepmind/deepmind-research — This project is an AI research implementation library and machine learning research repository. It provides a… aravindr93/mjrl — This package contains implementations of various RL algorithms for continuous control tasks simulated with MuJoCo. farama-foundation/metaworld — Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning.