Evaluating Generalization and Transfer Capacity of Multi-Agent Reinforcement Learning Across Variable Number of Agents

11/28/2021
by   Bengisu Guresti, et al.
0

Multi-agent Reinforcement Learning (MARL) problems often require cooperation among agents in order to solve a task. Centralization and decentralization are two approaches used for cooperation in MARL. While fully decentralized methods are prone to converge to suboptimal solutions due to partial observability and nonstationarity, the methods involving centralization suffer from scalability limitations and lazy agent problem. Centralized training decentralized execution paradigm brings out the best of these two approaches; however, centralized training still has an upper limit of scalability not only for acquired coordination performance but also for model size and training time. In this work, we adopt the centralized training with decentralized execution paradigm and investigate the generalization and transfer capacity of the trained models across variable number of agents. This capacity is assessed by training variable number of agents in a specific MARL problem and then performing greedy evaluations with variable number of agents for each training configuration. Thus, we analyze the evaluation performance for each combination of agent count for training versus evaluation. We perform experimental evaluations on predator prey and traffic junction environments and demonstrate that it is possible to obtain similar or higher evaluation performance by training with less agents. We conclude that optimal number of agents to perform training may differ from the target number of agents and argue that transfer across large number of agents can be a more efficient solution to scaling up than directly increasing number of agents during training.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/27/2023

Is Centralized Training with Decentralized Execution Framework Centralized Enough for MARL?

Centralized Training with Decentralized Execution (CTDE) has recently em...
research
02/15/2022

Disentangling Successor Features for Coordination in Multi-agent Reinforcement Learning

Multi-agent reinforcement learning (MARL) is a promising framework for s...
research
05/25/2022

Scalable Multi-Agent Model-Based Reinforcement Learning

Recent Multi-Agent Reinforcement Learning (MARL) literature has been lar...
research
04/25/2023

SEA: A Spatially Explicit Architecture for Multi-Agent Reinforcement Learning

Spatial information is essential in various fields. How to explicitly mo...
research
04/28/2023

From Explicit Communication to Tacit Cooperation:A Novel Paradigm for Cooperative MARL

Centralized training with decentralized execution (CTDE) is a widely-use...
research
08/04/2022

Transferable Multi-Agent Reinforcement Learning with Dynamic Participating Agents

We study multi-agent reinforcement learning (MARL) with centralized trai...
research
03/07/2022

Reinforcement Learning for Location-Aware Scheduling

Recent techniques in dynamical scheduling and resource management have f...

Please sign up or login with your details

Forgot password? Click here to reset