This is a minimal example to demonstrate how multi-agent reinforcement learning with differentiable communication channels and centralized critics can be realized in RLLib. This example serves as a reference implementation and starting point for making RLLib more compatible with such architectures.
☆43Sep 24, 2023Updated 2 years ago
Alternatives and similar repositories for rllib_differentiable_comms
Users that are interested in rllib_differentiable_comms are comparing it to the libraries listed below
Sorting:
- ☆32Apr 25, 2021Updated 4 years ago
- VMAS is a vectorized differentiable simulator designed for efficient Multi-Agent Reinforcement Learning benchmarking. It is comprised of …☆534Feb 8, 2026Updated last month
- Example Code for the Conditional Action Trees Paper☆12May 24, 2021Updated 4 years ago
- Official implementation of the UMDQN algorithm presented in the scientific research paper entitled "Distributional Reinforcement Learning…☆11Jun 3, 2022Updated 3 years ago
- Lux AI environment interface for RLlib multi-agents☆12Sep 23, 2021Updated 4 years ago
- Code for NeurIPS2023 accepted paper: Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning.☆40Feb 18, 2025Updated last year
- Deep memory and sequence models in JAX☆23Jan 15, 2026Updated 2 months ago
- Implementation of the MEPOL algorithm - A policy gradient method for task-agnostic exploration☆15Jul 6, 2023Updated 2 years ago
- ☆15Jul 27, 2023Updated 2 years ago
- BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL allows to quickly compare different MARL alg…☆586Feb 7, 2026Updated last month
- High-level nonlinear state-space control for multirotors and ground-robots. Freyja is suitable for vehicles that already have some stabil…☆18Oct 22, 2025Updated 4 months ago
- [CoRL'20] Learning a Decision Module by Imitating Driver’s Control Behaviors☆31Aug 5, 2022Updated 3 years ago
- ☆27Nov 5, 2025Updated 4 months ago
- The AI Arena: A framework for distributed multi-agent reinforcement learning☆14Aug 5, 2022Updated 3 years ago
- This project will work towards a fully-functional autonomous intelligent cyberdefense agent with increasingly advanced capabilities that …☆42Jan 20, 2025Updated last year
- Risk-sensitive Inverse Reinforcement Learning☆11Sep 11, 2019Updated 6 years ago
- An extension of the PyMARL codebase that includes additional algorithms and environment support☆699Sep 24, 2024Updated last year
- On the pitfalls of measuring emergent communication☆34Mar 12, 2019Updated 7 years ago
- Repo for reproduction of sequential social dilemmas☆415Mar 6, 2025Updated last year
- EA-HAS-Bench: Energy-Aware Hyperparameter and Architecture Search Benchmark (ICLR Spotlight 2023)☆18Dec 8, 2024Updated last year
- Official Implementation of 'UPDeT: Universal Multi-agent Reinforcement Learning via Policy Decoupling with Transformers' ICLR 2021(spotli…☆137Feb 3, 2021Updated 5 years ago
- ☆11Oct 25, 2021Updated 4 years ago
- An environment based on JSBSIM aimed at one-to-one close air combat.☆13May 15, 2023Updated 2 years ago
- Code repository for On the interaction between supervision and self-play in emergent communication (ICLR 2020)☆15Feb 4, 2020Updated 6 years ago
- Learning to Ground Multi-Agent Communication with Autoencoders [NeurIPS 2021]☆49Oct 29, 2021Updated 4 years ago
- Pytorch implementation of the paper 'Compositional language emerge in a neural iterated learning' (ICLR 2020).☆16Oct 14, 2021Updated 4 years ago
- Python library for solving reinforcement learning (RL) problems using generative models.☆11Feb 18, 2025Updated last year
- Benchmark Suite for Interpretable Rule Learning☆12Aug 23, 2020Updated 5 years ago
- Faithful Python implementation of the paper "Towards Deep Symbolic Reinforcement Learning" by Garnelo et al.☆13Mar 23, 2021Updated 4 years ago
- ☆20Aug 26, 2020Updated 5 years ago
- Fast Gradient Sign Method and Iterative Least-Likely Class, using LeNet and DenseNet in PyTorch☆10Nov 18, 2019Updated 6 years ago
- TTCP CAGE Challenge 3☆37Apr 1, 2024Updated last year
- Python wrapper for the Universal Robots ROS driver with Robotiq gripper support.☆14May 21, 2024Updated last year
- ☆15Feb 23, 2026Updated 3 weeks ago
- ☆11Jun 6, 2024Updated last year
- ☆10Jul 23, 2020Updated 5 years ago
- ☆13Aug 20, 2021Updated 4 years ago
- reveal-md is great project. Improve your presentation even more with custom user scripts. Here is the place to find them.☆15Dec 7, 2023Updated 2 years ago
- [CoRL 2024] Official repository for: "CtRL-Sim: Reactive and Controllable Driving Agents with Offline Reinforcement Learning"☆60Oct 4, 2024Updated last year