proroklab / VectorizedMultiAgentSimulator
VMAS is a vectorized differentiable simulator designed for efficient Multi-Agent Reinforcement Learning benchmarking. It is comprised of a vectorized 2D physics engine written in PyTorch and a set of challenging multi-robot scenarios. Additional scenarios can be implemented through a simple and modular interface.
☆344Updated 2 weeks ago
Related projects ⓘ
Alternatives and complementary repositories for VectorizedMultiAgentSimulator
- A collection of MARL benchmarks based on TorchRL☆282Updated last week
- Multi-objective Gymnasium environments for reinforcement learning☆289Updated 3 weeks ago
- Multi-Objective Reinforcement Learning algorithms implementations.☆313Updated 3 weeks ago
- Multi-Robot Warehouse (RWARE): A multi-agent reinforcement learning environment☆313Updated 2 months ago
- An extension of the PyMARL codebase that includes additional algorithms and environment support☆512Updated last month
- Level-based Foraging (LBF): A multi-agent environment for RL☆161Updated 2 months ago
- Benchmark for Continuous Multi-Agent Robotic Control, based on OpenAI's Mujoco Gym environments.☆331Updated last year
- ☆216Updated 9 months ago
- SBX: Stable Baselines Jax (SB3 + Jax)☆343Updated this week
- An engine for high performance multi-agent environments with very large numbers of agents, along with a set of reference environments☆229Updated 2 weeks ago
- Multi-Agent Reinforcement Learning with JAX☆441Updated 2 weeks ago
- Datasets with baselines for offline multi-agent reinforcement learning.☆140Updated last week
- Lightweight multi-agent gridworld Gym environment☆198Updated last year
- ☆201Updated 9 months ago
- Simple (but often Strong) Baselines for POMDPs in PyTorch, ICML 2022☆306Updated 2 months ago
- A standard format for offline reinforcement learning datasets, with popular reference datasets and related utilities☆295Updated 2 weeks ago
- Implementation of Dreamer v3 in pytorch.☆426Updated last month
- Baseline implementation of recurrent PPO using truncated BPTT☆125Updated 6 months ago
- Clean baseline implementation of PPO using an episodic TransformerXL memory☆152Updated 5 months ago
- Benchmarks for Multi-Objective Multi-Agent Decision Making☆72Updated 3 weeks ago
- Deep Transformer Q-Networks for Partially Observable Reinforcement Learning☆148Updated 4 months ago
- Multi-Agent Constrained Policy Optimisation (MACPO; MAPPO-L).☆145Updated 7 months ago
- Modular reinforcement learning library (on PyTorch and JAX) with support for NVIDIA Isaac Gym, Omniverse Isaac Gym and Isaac Lab☆561Updated 2 weeks ago
- Partially Observable Process Gym☆167Updated 4 months ago
- A collection of robotics simulation environments for reinforcement learning☆571Updated 2 weeks ago
- A repository of high-performing hierarchical reinforcement learning models and algorithms.☆281Updated last year
- An engine to create high performance multi-agent grid world environments with hundreds or thousands of agents, along with a set of refere…☆190Updated 2 years ago
- An elegant PyTorch offline reinforcement learning library for researchers.☆281Updated 7 months ago
- NeurIPS 2023: Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark☆395Updated 6 months ago
- Author's PyTorch implementation of TD3+BC, a simple variant of TD3 for offline RL☆327Updated 2 years ago