A library of reinforcement learning components and agents
☆3,946Mar 12, 2026Updated last week
Alternatives and similar repositories for acme
Users that are interested in acme are comparing it to the libraries listed below
Sorting:
- Reverb is an efficient and easy-to-use data storage and transport system designed for machine learning research☆768Mar 9, 2026Updated last week
- ☆1,411Mar 2, 2026Updated 2 weeks ago
- JAX-based neural network library☆3,197Mar 12, 2026Updated last week
- A Python interface for reinforcement learning environments☆397Dec 23, 2022Updated 3 years ago
- bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent☆1,531Apr 13, 2024Updated last year
- Reinforcement Learning in PyTorch☆2,274Jan 4, 2021Updated 5 years ago
- SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference. Implements IMPALA and R2D2 algorithms in TF2 with SEED's arch…☆837Nov 29, 2022Updated 3 years ago
- Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.☆4,498Updated this week
- OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.☆5,072Mar 9, 2026Updated last week
- Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.☆10,854Nov 4, 2024Updated last year
- PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.☆12,925Updated this week
- This repository contains implementations and illustrative code to accompany DeepMind publications☆14,765Updated this week
- A fork of OpenAI Baselines, implementations of reinforcement learning algorithms☆4,324Sep 4, 2022Updated 3 years ago
- Massively parallel rigidbody physics simulation on accelerator hardware.☆3,094Updated this week
- TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.☆2,995Jan 16, 2026Updated 2 months ago
- OpenAI Baselines: high-quality implementations of reinforcement learning algorithms☆16,668Aug 1, 2024Updated last year
- A toolkit for reproducible reinforcement learning research.☆2,088May 4, 2023Updated 2 years ago
- [NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.☆867Aug 12, 2024Updated last year
- Collection of reinforcement learning algorithms☆2,877Jun 17, 2024Updated last year
- High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, T…☆9,327Jul 8, 2025Updated 8 months ago
- C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.☆1,279Aug 12, 2024Updated last year
- Simple and easily configurable grid world environments for reinforcement learning☆2,412Mar 2, 2026Updated 2 weeks ago
- Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more☆35,108Updated this week
- A platform for Reasoning systems (Reinforcement Learning, Contextual Bandits, etc.)☆3,686Updated this week
- Flax is a neural network library for JAX that is designed for flexibility.☆7,127Updated this week
- A collection of reference environments for offline reinforcement learning☆1,662Nov 18, 2024Updated last year
- A PyTorch Platform for Distributed RL☆751Sep 15, 2021Updated 4 years ago
- DQN Zoo is a collection of reference implementations of reinforcement learning agents developed at DeepMind based on the Deep Q-Network (…☆495Apr 6, 2024Updated last year
- ☆330Aug 22, 2023Updated 2 years ago
- Library for Model Based RL☆1,058Jul 12, 2024Updated last year
- JAX (Flax) implementation of algorithms for Deep Reinforcement Learning with continuous action spaces.☆753Oct 26, 2022Updated 3 years ago
- An educational resource to help anyone learn deep reinforcement learning.☆11,660Aug 5, 2024Updated last year
- RL Environments in JAX 🌍☆871May 30, 2025Updated 9 months ago
- TensorFlow Reinforcement Learning☆3,136Dec 8, 2022Updated 3 years ago
- An API standard for multi-agent reinforcement learning environments, with popular reference environments and related utilities☆3,351Feb 6, 2026Updated last month
- Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.☆41,799Updated this week
- Really Fast End-to-End Jax RL Implementations☆1,032Sep 9, 2024Updated last year
- MuZero☆2,785Sep 3, 2024Updated last year
- TensorFlow-based neural network library☆9,906Feb 10, 2026Updated last month