instadeepai / jumanjiLinks
đšī¸ A diverse suite of scalable reinforcement learning environments in JAX
â731Updated 3 weeks ago
Alternatives and similar repositories for jumanji
Users that are interested in jumanji are comparing it to the libraries listed below
Sorting:
- Accelerated Quality-Diversityâ301Updated this week
- RL Environments in JAX đâ758Updated last week
- đĻ A research-friendly codebase for fast experimentation of multi-agent reinforcement learning in JAXâ796Updated last week
- đī¸A research-friendly codebase for fast experimentation of single-agent reinforcement learning in JAX âĸ End-to-End JAX RLâ328Updated this week
- Multi-Agent Reinforcement Learning with JAXâ581Updated this week
- ⥠Flashbax: Accelerated Replay Buffers in JAXâ236Updated 2 months ago
- Really Fast End-to-End Jax RL Implementationsâ882Updated 8 months ago
- JAX (Flax) implementation of algorithms for Deep Reinforcement Learning with continuous action spaces.â684Updated 2 years ago
- [NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.â831Updated 9 months ago
- Evolution Strategies in JAX đĻâ624Updated last week
- SBX: Stable Baselines Jax (SB3 + Jax) RL algorithmsâ455Updated 2 weeks ago
- Multi-objective Gymnasium environments for reinforcement learningâ326Updated 3 months ago
- âī¸ Vectorized RL game environments in JAXâ480Updated 2 months ago
- đââŦ Contextual bandits library for continuous action trees with smoothing in JAXâ66Updated 2 years ago
- (Crafter + NetHack) in JAX. ICML 2024 Spotlight.â314Updated last week
- Hardware-Accelerated Reinforcement Learning Algorithms in pure Jax!â217Updated last week
- A suite of test scenarios for multi-agent reinforcement learning.â705Updated last week
- A standard format for offline reinforcement learning datasets, with popular reference datasets and related utilitiesâ393Updated last week
- DQN Zoo is a collection of reference implementations of reinforcement learning agents developed at DeepMind based on the Deep Q-Network (âĻâ472Updated last year
- Library for Model Based RLâ998Updated 10 months ago
- A collection of MARL benchmarks based on TorchRLâ400Updated 3 weeks ago
- A grid-world game engine for game AI researchâ241Updated last year
- â1,320Updated 3 weeks ago
- An engine for high performance multi-agent environments with very large numbers of agents, along with a set of reference environmentsâ290Updated 3 months ago
- Distributed Reinforcement Learning accelerated by Lightning Fabricâ377Updated last week
- â229Updated 6 months ago
- A Python interface for reinforcement learning environmentsâ367Updated 2 years ago
- An API conversion tool for popular external reinforcement learning environmentsâ166Updated 4 months ago
- High throughput synchronous and asynchronous reinforcement learningâ904Updated last week
- LeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.â578Updated 7 months ago