Causal Mean Field Multi-Agent Reinforcement Learning
- URL: http://arxiv.org/abs/2502.14200v1
- Date: Thu, 20 Feb 2025 02:15:58 GMT
- Title: Causal Mean Field Multi-Agent Reinforcement Learning
- Authors: Hao Ma, Zhiqiang Pu, Yi Pan, Boyin Liu, Junlong Gao, Zhenyu Guo,
- Abstract summary: A framework named mean-field reinforcement learning (MFRL) could alleviate the scalability problem by employing the Mean Field Theory.
This framework lacks the ability to identify essential interactions under nonstationary environments.
We propose an algorithm called causal mean-field Q-learning (CMFQ) to address the scalability problem.
- Score: 10.767740092703777
- License:
- Abstract: Scalability remains a challenge in multi-agent reinforcement learning and is currently under active research. A framework named mean-field reinforcement learning (MFRL) could alleviate the scalability problem by employing the Mean Field Theory to turn a many-agent problem into a two-agent problem. However, this framework lacks the ability to identify essential interactions under nonstationary environments. Causality contains relatively invariant mechanisms behind interactions, though environments are nonstationary. Therefore, we propose an algorithm called causal mean-field Q-learning (CMFQ) to address the scalability problem. CMFQ is ever more robust toward the change of the number of agents though inheriting the compressed representation of MFRL's action-state space. Firstly, we model the causality behind the decision-making process of MFRL into a structural causal model (SCM). Then the essential degree of each interaction is quantified via intervening on the SCM. Furthermore, we design the causality-aware compact representation for behavioral information of agents as the weighted sum of all behavioral information according to their causal effects. We test CMFQ in a mixed cooperative-competitive game and a cooperative game. The result shows that our method has excellent scalability performance in both training in environments containing a large number of agents and testing in environments containing much more agents.
Related papers
- AgentAlign: Misalignment-Adapted Multi-Agent Perception for Resilient Inter-Agent Sensor Correlations [8.916036880001734]
Existing research overlooks the fragile multi-sensor correlations in multi-agent settings.
AgentAlign is a real-world heterogeneous agent cross-modality feature alignment framework.
We present a novel V2XSet-noise dataset that simulates realistic sensor imperfections under diverse environmental conditions.
arXiv Detail & Related papers (2024-12-09T01:51:18Z) - Model-Based RL for Mean-Field Games is not Statistically Harder than Single-Agent RL [57.745700271150454]
We study the sample complexity of reinforcement learning in Mean-Field Games (MFGs) with model-based function approximation.
We introduce the Partial Model-Based Eluder Dimension (P-MBED), a more effective notion to characterize the model class complexity.
arXiv Detail & Related papers (2024-02-08T14:54:47Z) - On the Complexity of Multi-Agent Decision Making: From Learning in Games
to Partial Monitoring [105.13668993076801]
A central problem in the theory of multi-agent reinforcement learning (MARL) is to understand what structural conditions and algorithmic principles lead to sample-efficient learning guarantees.
We study this question in a general framework for interactive decision making with multiple agents.
We show that characterizing the statistical complexity for multi-agent decision making is equivalent to characterizing the statistical complexity of single-agent decision making.
arXiv Detail & Related papers (2023-05-01T06:46:22Z) - Residual Q-Networks for Value Function Factorizing in Multi-Agent
Reinforcement Learning [0.0]
We propose a novel concept of Residual Q-Networks (RQNs) for Multi-Agent Reinforcement Learning (MARL)
The RQN learns to transform the individual Q-value trajectories in a way that preserves the Individual-Global-Max criteria (IGM)
The proposed method converges faster, with increased stability and shows robust performance in a wider family of environments.
arXiv Detail & Related papers (2022-05-30T16:56:06Z) - ROMAX: Certifiably Robust Deep Multiagent Reinforcement Learning via
Convex Relaxation [32.091346776897744]
Cyber-physical attacks can challenge the robustness of multiagent reinforcement learning.
We propose a minimax MARL approach to infer the worst-case policy update of other agents.
arXiv Detail & Related papers (2021-09-14T16:18:35Z) - Efficient Model-Based Multi-Agent Mean-Field Reinforcement Learning [89.31889875864599]
We propose an efficient model-based reinforcement learning algorithm for learning in multi-agent systems.
Our main theoretical contributions are the first general regret bounds for model-based reinforcement learning for MFC.
We provide a practical parametrization of the core optimization problem.
arXiv Detail & Related papers (2021-07-08T18:01:02Z) - Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning [92.05556163518999]
MARL exacerbates matters by imposing various constraints on communication and observability.
For value-based methods, it poses challenges in accurately representing the optimal value function.
For policy gradient methods, it makes training the critic difficult and exacerbates the problem of the lagging critic.
We show that from a learning theory perspective, both problems can be addressed by accurately representing the associated action-value function.
arXiv Detail & Related papers (2021-05-31T23:08:05Z) - Permutation Invariant Policy Optimization for Mean-Field Multi-Agent
Reinforcement Learning: A Principled Approach [128.62787284435007]
We propose the mean-field proximal policy optimization (MF-PPO) algorithm, at the core of which is a permutation-invariant actor-critic neural architecture.
We prove that MF-PPO attains the globally optimal policy at a sublinear rate of convergence.
In particular, we show that the inductive bias introduced by the permutation-invariant neural architecture enables MF-PPO to outperform existing competitors.
arXiv Detail & Related papers (2021-05-18T04:35:41Z) - FACMAC: Factored Multi-Agent Centralised Policy Gradients [103.30380537282517]
We propose FACtored Multi-Agent Centralised policy gradients (FACMAC)
It is a new method for cooperative multi-agent reinforcement learning in both discrete and continuous action spaces.
We evaluate FACMAC on variants of the multi-agent particle environments, a novel multi-agent MuJoCo benchmark, and a challenging set of StarCraft II micromanagement tasks.
arXiv Detail & Related papers (2020-03-14T21:29:09Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.