Models As Agents: Optimizing Multi-step Predictions Of Interactive Local Models In Model-based Multi-agent Reinforcement Learning
2023 · Zifan Wu, Chao Yu, Chen Chen, et al.
Abstract
Research in model-based reinforcement learning has made significant progress in recent years. Compared to single-agent settings, the exponential dimension growth of the joint state-action space in multi-agent systems dramatically increases the complexity of the environment dynamics, which makes it infeasible to learn an accurate global model and thus necessitates the use of agent-wise local models. However, during multi-step model rollouts, the prediction of one local model can affect the predictions of other local models in the next step. As a result, local prediction errors can be propagated to other localities and eventually give rise to considerably large global errors. Furthermore, since the models are generally used to predict for multiple steps, simply minimizing one-step prediction errors regardless of their long-term effect on other models may further aggravate the propagation of local errors. To this end, we propose Models as AGents (MAG), a multi-agent model optimization fra
Authors
(none)
Tags
Stats
Related papers
- Towards A Simple Approach To Multi-step Model-based Reinforcement Learning (2018)0.00
- Partial Models For Building Adaptive Model-based Reinforcement Learning Agents (2024)0.00
- A Structured Prediction Approach For Generalization In Cooperative Multi-agent Reinforcement Learning (2019)0.00
- Mingling Foresight With Imagination: Model-based Cooperative Multi-agent Reinforcement Learning (2022)0.00
- Model-based Multi-agent Reinforcement Learning: Recent Progress And Prospects (2022)0.00
- Learning With Imperfect Models: When Multi-step Prediction Mitigates Compounding Error (2025)0.00
- Model-based Multi-agent Policy Optimization With Adaptive Opponent-wise Rollouts (2021)0.00
- Efficient Model-based Multi-agent Reinforcement Learning Via Optimistic Equilibrium Computation (2022)0.00