Parameter Sharing Deep Deterministic Policy Gradient for Cooperative Multi-agent Reinforcement Learning

2017-10-01 · Xiangxiang Chu, Hangjun Ye

Deep reinforcement learning for multi-agent cooperation and competition has been a hot topic recently. This paper focuses on cooperative multi-agent problem based on actor-critic methods under local observations settings. Multi agent deep deterministic policy gradient obtained state of art results for some multi-agent games, whereas, it cannot scale well with growing amount of agents. In order to boost scalability, we propose a parameter sharing deterministic policy gradient method with three variants based on neural networks, including actor-critic sharing, actor sharing and actor sharing with partially shared critic. Benchmarks from rllab show that the proposed method has advantages in learning speed and memory efficiency, well scales with growing amount of agents, and moreover, it can make full use of reward sharing and exchangeability if possible.

📄 PDF Abstract BibTeX arXiv:1710.00336

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement LearningMulti-agent Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Improving monotonic optimization in heterogeneous multi-agent reinforcement learning with optimal marginal deterministic policy gradient

2025-07-14 · Xiaoyang Yu, Youfang Lin, Shuo Wang, Sheng Han arxiv

In heterogeneous multi-agent reinforcement learning (MARL), achieving monotonic improvement plays a pivotal role in enhancing performance. The HAPPO algorithm proposes a feasible solution by introducing a sequential upda…

Multi-agent Reinforcement Learning

Energy Management in a Cooperative Energy Harvesting Wireless Sensor Network

2023-10-09 · Arghyadeep Barat, Prabuchandran. K. J, Shalabh Bhatnagar

In this paper, we consider the problem of finding an optimal energy management policy for a network of sensor nodes capable of harvesting their own energy and sharing it with other nodes in the network. We formulate this…

energy management Management

HyperMARL: Adaptive Hypernetworks for Multi-Agent RL

2024-12-05 · Kale-ab Abebe Tessera, Arrasy Rahman, Amos Storkey, Stefano V. Albrecht

Adaptability to specialised or homogeneous behaviours is critical in cooperative multi-agent reinforcement learning (MARL). Parameter sharing (PS) techniques, common for efficient adaptation, often limit behavioural dive…

Diversity Multi-agent Reinforcement Learning

Wasserstein-Barycenter Consensus for Cooperative Multi-Agent Reinforcement Learning

2025-06-14 · Ali Baheri

Cooperative multi-agent reinforcement learning (MARL) demands principled mechanisms to align heterogeneous policies while preserving the capacity for specialized behavior. We introduce a novel consensus framework that de…

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning

Collaboration of AI Agents via Cooperative Multi-Agent Deep Reinforcement Learning

2019-06-30 · Niranjan Balachandar, Justin Dieter, Govardana Sachithanandam Ramachandran

There are many AI tasks involving multiple interacting agents where agents should learn to cooperate and collaborate to effectively perform the task. Here we develop and evaluate various multi-agent protocols to train ag…

counterfactual Deep Reinforcement Learning reinforcement-learning Reinforcement Learning+1