Multi-agent Reinforcement Learning
387 papers with code • 3 benchmarks • 9 datasets
The target of Multi-agent Reinforcement Learning is to solve complex problems by integrating multiple agents that focus on different sub-tasks. In general, there are two types of multi-agent systems: independent and cooperative systems.
Source: Show, Describe and Conclude: On Exploiting the Structure Information of Chest X-Ray Reports
Benchmarks
These leaderboards are used to track progress in Multi-agent Reinforcement Learning
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
Libraries
Use these libraries to find Multi-agent Reinforcement Learning models and implementationsDatasets
CityFlow
StarCraft II Learning Environment
SMAC-Exp
Hanabi Learning Environment
OG-MARL
pursuitMW
ColosseumRL
Latest papers
Laser Learning Environment: A new environment for coordination-critical multi-agent tasks
We introduce the Laser Learning Environment (LLE), a collaborative multi-agent reinforcement learning environment in which coordination is central.
GOV-REK: Governed Reward Engineering Kernels for Designing Robust Multi-Agent Reinforcement Learning Systems
For multi-agent reinforcement learning systems (MARLS), the problem formulation generally involves investing massive reward engineering effort specific to a given problem.
Inferring Latent Temporal Sparse Coordination Graph for Multi-Agent Reinforcement Learning
Wei9711/LTSCG
•
•
The LTS-CG leverages agents' historical observations to calculate an agent-pair probability matrix, where a sparse graph is sampled from and used for knowledge exchange between agents, thereby simultaneously capturing agent dependencies and relation uncertainty.
Ensembling Prioritized Hybrid Policies for Multi-agent Pathfinding
ai4co/eph-mapf
•
•
We first propose a selective communication block to gather richer information for better agent coordination within multi-agent environments and train the model with a Q-learning-based algorithm.
Generalising Multi-Agent Cooperation through Task-Agnostic Communication
proroklab/task-agnostic-comms
•
•
Our objective is to learn a fixed-size latent Markov state from a variable number of agent observations.
PPS-QMIX: Periodically Parameter Sharing for Accelerating Convergence of Multi-Agent Reinforcement Learning
Agents share Q-value network periodically during the training process.
Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning
hyunghona/emu
•
•
To address this, we introduce Efficient episodic Memory Utilization (EMU) for MARL, with two primary objectives: (a) accelerating reinforcement learning by leveraging semantically coherent memory from an episodic buffer and (b) selectively promoting desirable transitions to prevent local convergence.
Independent Learning in Constrained Markov Potential Games
We propose an independent policy gradient algorithm for learning approximate constrained Nash equilibria: Each agent observes their own actions and rewards, along with a shared state.
Modelling crypto markets by multi-agent reinforcement learning
Building on a previous foundation work (Lussange et al. 2020), this study introduces a multi-agent reinforcement learning (MARL) model simulating crypto markets, which is calibrated to the Binance's daily closing prices of $153$ cryptocurrencies that were continuously traded between 2018 and 2022.
Risk-Sensitive Multi-Agent Reinforcement Learning in Network Aggregative Markov Games
Under a set of assumptions, we prove the convergence of the algorithm to a subjective notion of Markov perfect Nash equilibrium in NAMGs.
