Models as Agents: Optimizing Multi-Step Predictions of Interactive Local Models in Model-Based Multi-Agent Reinforcement Learning
نویسندگان
چکیده
Research in model-based reinforcement learning has made significant progress recent years. Compared to single-agent settings, the exponential dimension growth of joint state-action space multi-agent systems dramatically increases complexity environment dynamics, which makes it infeasible learn an accurate global model and thus necessitates use agent-wise local models. However, during multi-step rollouts, prediction one can affect predictions other models next step. As a result, errors be propagated localities eventually give rise considerably large errors. Furthermore, since are generally used predict for multiple steps, simply minimizing one-step regardless their long-term effect on may further aggravate propagation To this end, we propose Models as AGents (MAG), optimization framework that reversely treats decision making agents current policies dynamics rollout process. In way, able consider mutual between each before predictions. Theoretically, show objective MAG is approximately equivalent maximizing lower bound true return. Experiments challenging StarCraft II benchmark demonstrate effectiveness MAG.
منابع مشابه
Multi-Agent Reinforcement Learning
This thesis presents a novel approach to provide adaptive mechanisms to detect and categorise Flooding-Base DoS (FBDoS) and Flooding-Base DDoS (FBDDoS) attacks. These attacks are generally based on a flood of packets with the intention of overfilling key resources of the target, and today the attacks have the capability to disrupt networks of almost any size. To address this problem we propose ...
متن کاملMulti-Time Models for Reinforcement Learning
Reinforcement learning can be used not only to predict rewards, but also to predict states, i.e. to learn a model of the world's dynamics. Models can be deened at diierent levels of temporal abstraction. Multi-time models are models that focus on predicting what will happen, rather than when a certain event will take place. Based on multi-time models, we can deene abstract actions, which enable...
متن کاملMulti Agent Learning of Relational Action Models
Multi Agent Relational Action Learning considers a community of agents, each rationally acting following some relational action model. The observed effect of past actions that led an agent to revise its action model can be communicated, upon request, to another agent, speeding up its own revision. We present a framework for such collaborative relational action model revision.
متن کاملFully Decentralized Multi-Agent Reinforcement Learning with Networked Agents
We consider the problem of fully decentralized multi-agent reinforcement learning (MARL), where the agents are located at the nodes of a time-varying communication network. Specifically, we assume that the reward functions of the agents might correspond to different tasks, and are only known to the corresponding agent. Moreover, each agent makes individual decisions based on both the informatio...
متن کاملMulti-Agent Deep Reinforcement Learning
This work introduces a novel approach for solving reinforcement learning problems in multi-agent settings. We propose a state reformulation of multi-agent problems in R that allows the system state to be represented in an image-like fashion. We then apply deep reinforcement learning techniques with a convolution neural network as the Q-value function approximator to learn distributed multi-agen...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Proceedings of the ... AAAI Conference on Artificial Intelligence
سال: 2023
ISSN: ['2159-5399', '2374-3468']
DOI: https://doi.org/10.1609/aaai.v37i9.26241