Multi-agent Deep Reinforcement Learning With Extremely Noisy Observations

Abstract

Multi-agent reinforcement learning systems aim to provide interacting agents with the ability to collaboratively learn and adapt to the behaviour of other agents. In many real-world applications, the agents can only acquire a partial view of the world. Here we consider a setting whereby most agents' observations are also extremely noisy, hence only weakly correlated to the true state of the environment. Under these circumstances, learning an optimal policy becomes particularly challenging, even in the unrealistic case that an agent's policy can be made conditional upon all other agents' observations. To overcome these difficulties, we propose a multi-agent deep deterministic policy gradient algorithm enhanced by a communication medium (MADDPG-M), which implements a two-level, concurrent learning mechanism. An agent's policy depends on its own private observations as well as those explicitly shared by others through a communication medium. At any given point in time, an agent must decid

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keykilinc2018multi

Related papers

• Noise Distribution Decomposition Based Multi-agent Distributional Reinforcement Learning (2023)0.00
• Deep Multiagent Reinforcement Learning: Challenges And Directions (2021)0.00
• Descent-guided Policy Gradient For Scalable Cooperative Multi-agent Learning (2026)0.00
• Multi-agent Deep Reinforcement Learning (MADRL) Meets Multi-user MIMO Systems (2021)7.50
• Deep Decentralized Multi-task Multi-agent Reinforcement Learning Under Partial Observability (2017)0.00
• Scalable Centralized Deep Multi-agent Reinforcement Learning Via Policy Gradients (2018)0.00
• Distributed Multi-agent Deep Reinforcement Learning For Robust Coordination Against Noise (2022)5.84
• Sample-efficient Distributionally Robust Multi-agent Reinforcement Learning Via Online Interaction (2025)0.00