Safe Multi-Agent Reinforcement Learning with Convergence to Generalized Nash Equilibrium

• URL: http://arxiv.org/abs/2411.15036v1
• Date: Fri, 22 Nov 2024 16:08:42 GMT
• Title: Safe Multi-Agent Reinforcement Learning with Convergence to Generalized Nash Equilibrium
• Authors: Zeyang Li, Navid Azizan,
• Abstract summary: Multi-agent reinforcement learning (MARL) has achieved notable success in cooperative tasks. deploying MARL agents in real-world applications presents critical safety challenges. We propose a novel theoretical framework for safe MARL with $textitstate-wise$ constraints, where safety requirements are enforced at every state the agents visit. For practical deployment in complex high-dimensional systems, we propose $textitMulti-Agent Dual Actor-Critic$ (MADAC)
• Score: 6.169364905804677
• License:
• Abstract: Multi-agent reinforcement learning (MARL) has achieved notable success in cooperative tasks, demonstrating impressive performance and scalability. However, deploying MARL agents in real-world applications presents critical safety challenges. Current safe MARL algorithms are largely based on the constrained Markov decision process (CMDP) framework, which enforces constraints only on discounted cumulative costs and lacks an all-time safety assurance. Moreover, these methods often overlook the feasibility issue (the system will inevitably violate state constraints within certain regions of the constraint set), resulting in either suboptimal performance or increased constraint violations. To address these challenges, we propose a novel theoretical framework for safe MARL with $\textit{state-wise}$ constraints, where safety requirements are enforced at every state the agents visit. To resolve the feasibility issue, we leverage a control-theoretic notion of the feasible region, the controlled invariant set (CIS), characterized by the safety value function. We develop a multi-agent method for identifying CISs, ensuring convergence to a Nash equilibrium on the safety value function. By incorporating CIS identification into the learning process, we introduce a multi-agent dual policy iteration algorithm that guarantees convergence to a generalized Nash equilibrium in state-wise constrained cooperative Markov games, achieving an optimal balance between feasibility and performance. Furthermore, for practical deployment in complex high-dimensional systems, we propose $\textit{Multi-Agent Dual Actor-Critic}$ (MADAC), a safe MARL algorithm that approximates the proposed iteration scheme within the deep RL paradigm. Empirical evaluations on safe MARL benchmarks demonstrate that MADAC consistently outperforms existing methods, delivering much higher rewards while reducing constraint violations.

Related papers

• Uniformly Safe RL with Objective Suppression for Multi-Constraint Safety-Critical Applications [73.58451824894568]
  The widely adopted CMDP model constrains the risks in expectation, which makes room for dangerous behaviors in long-tail states. In safety-critical domains, such behaviors could lead to disastrous outcomes. We propose Objective Suppression, a novel method that adaptively suppresses the task reward maximizing objectives according to a safety critic.
  arXiv  Detail & Related papers  (2024-02-23T23:22:06Z)
• QFree: A Universal Value Function Factorization for Multi-Agent Reinforcement Learning [2.287186762346021]
  We propose QFree, a universal value function factorization method for multi-agent reinforcement learning. We show that QFree achieves the state-of-the-art performance in a general-purpose complex MARL benchmark environment.
  arXiv  Detail & Related papers  (2023-11-01T08:07:16Z)
• Safe Model-Based Multi-Agent Mean-Field Reinforcement Learning [48.667697255912614]
  Mean-field reinforcement learning addresses the policy of a representative agent interacting with the infinite population of identical agents. We propose Safe-M$3$-UCRL, the first model-based mean-field reinforcement learning algorithm that attains safe policies even in the case of unknown transitions. Our algorithm effectively meets the demand in critical areas while ensuring service accessibility in regions with low demand.
  arXiv  Detail & Related papers  (2023-06-29T15:57:07Z)
• Provably Learning Nash Policies in Constrained Markov Potential Games [90.87573337770293]
  Multi-agent reinforcement learning (MARL) addresses sequential decision-making problems with multiple agents. Constrained Markov Games (CMGs) are a natural formalism for safe MARL problems, though generally intractable.
  arXiv  Detail & Related papers  (2023-06-13T13:08:31Z)
• Interpreting Primal-Dual Algorithms for Constrained Multiagent Reinforcement Learning [4.67306371596399]
  Most C-MARL algorithms use a primal-dual approach to enforce constraints through a penalty function added to the reward. We show that the standard practice of using the constraint function as the penalty leads to a weak notion of safety. We propose a constrained multiagent advantage actor critic (C-MAA2C) algorithm.
  arXiv  Detail & Related papers  (2022-11-29T10:23:26Z)
• Latent State Marginalization as a Low-cost Approach for Improving Exploration [79.12247903178934]
  We propose the adoption of latent variable policies within the MaxEnt framework. We show that latent variable policies naturally emerges under the use of world models with a latent belief state. We experimentally validate our method on continuous control tasks, showing that effective marginalization can lead to better exploration and more robust training.
  arXiv  Detail & Related papers  (2022-10-03T15:09:12Z)
• Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environments [84.3830478851369]
  We propose a safe reinforcement learning approach that can jointly learn the environment and optimize the control policy. Our approach can effectively enforce hard safety constraints and significantly outperform CMDP-based baseline methods in system safe rate measured via simulations.
  arXiv  Detail & Related papers  (2022-09-29T20:49:25Z)
• Multi-Agent Constrained Policy Optimisation [17.772811770726296]
  We formulate the safe MARL problem as a constrained Markov game and solve it with policy optimisation methods. Our solutions -- Multi-Agent Constrained Policy optimisation (MACPO) and MAPPO-Lagrangian -- leverage the theories from both constrained policy optimisation and multi-agent trust region learning. We develop the benchmark suite of Safe Multi-Agent MuJoCo that involves a variety of MARL baselines.
  arXiv  Detail & Related papers  (2021-10-06T14:17:09Z)
• Lyapunov-based uncertainty-aware safe reinforcement learning [0.0]
  InReinforcement learning (RL) has shown a promising performance in learning optimal policies for a variety of sequential decision-making tasks. In many real-world RL problems, besides optimizing the main objectives, the agent is expected to satisfy a certain level of safety. We propose a Lyapunov-based uncertainty-aware safe RL model to address these limitations.
  arXiv  Detail & Related papers  (2021-07-29T13:08:15Z)
• Softmax with Regularization: Better Value Estimation in Multi-Agent Reinforcement Learning [72.28520951105207]
  Overestimation in $Q$-learning is an important problem that has been extensively studied in single-agent reinforcement learning. We propose a novel regularization-based update scheme that penalizes large joint action-values deviating from a baseline. We show that our method provides a consistent performance improvement on a set of challenging StarCraft II micromanagement tasks.
  arXiv  Detail & Related papers  (2021-03-22T14:18:39Z)
• Constrained Markov Decision Processes via Backward Value Functions [43.649330976089004]
  We model the problem of learning with constraints as a Constrained Markov Decision Process. A key contribution of our approach is to translate cumulative cost constraints into state-based constraints. We provide theoretical guarantees under which the agent converges while ensuring safety over the course of training.
  arXiv  Detail & Related papers  (2020-08-26T20:56:16Z)

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.