PIC: Permutation Invariant Critic For Multi-agent Deep Reinforcement Learning

Abstract

Sample efficiency and scalability to a large number of agents are two important goals for multi-agent reinforcement learning systems. Recent works got us closer to those goals, addressing non-stationarity of the environment from a single agent's perspective by utilizing a deep net critic which depends on all observations and actions. The critic input concatenates agent observations and actions in a user-specified order. However, since deep nets aren't permutation invariant, a permuted input changes the critic output despite the environment remaining identical. To avoid this inefficiency, we propose a 'permutation invariant critic' (PIC), which yields identical output irrespective of the agent permutation. This consistent representation enables our model to scale to 30 times more agents and to achieve improvements of test episode reward between 15% to 50% on the challenging multi-agent particle environment (MPE).

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyliu2019pic

Related papers

• Permutation Invariant Policy Optimization For Mean-field Multi-agent Reinforcement Learning: A Principled Approach (2021)0.00
• Spectra: Scalable Multi-agent Reinforcement Learning With Permutation-free Networks (2025)0.00
• Actor-attention-critic For Multi-agent Reinforcement Learning (2018)0.00
• Scalable Neighborhood-based Multi-agent Actor-critic (2026)0.00
• Multi-agent Actor-critic For Mixed Cooperative-competitive Environments (2017)0.00
• HARP: Human-assisted Regrouping With Permutation Invariant Critic For Multi-agent Reinforcement Learning (2024)0.00
• Local Advantage Actor-critic For Robust Multi-agent Deep Reinforcement Learning (2021)7.81
• The Reactor: A Fast And Sample-efficient Actor-critic Agent For Reinforcement Learning (2017)0.00