Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing

• URL: http://arxiv.org/abs/2102.07475v1
• Date: Mon, 15 Feb 2021 11:33:52 GMT
• Title: Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing
• Authors: Filippos Christianos, Georgios Papoudakis, Arrasy Rahman, Stefano V. Albrecht
• Abstract summary: Sharing parameters in deep reinforcement learning has played an essential role in allowing algorithms to scale to a large number of agents. However, having all agents share the same parameters can also have a detrimental effect on learning. We propose a novel method to automatically identify agents which may benefit from sharing parameters by partitioning them based on their abilities and goals.
• Score: 4.855663359344748
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Sharing parameters in multi-agent deep reinforcement learning has played an essential role in allowing algorithms to scale to a large number of agents. Parameter sharing between agents significantly decreases the number of trainable parameters, shortening training times to tractable levels, and has been linked to more efficient learning. However, having all agents share the same parameters can also have a detrimental effect on learning. We demonstrate the impact of parameter sharing methods on training speed and converged returns, establishing that when applied indiscriminately, their effectiveness is highly dependent on the environment. Therefore, we propose a novel method to automatically identify agents which may benefit from sharing parameters by partitioning them based on their abilities and goals. Our approach combines the increased sample efficiency of parameter sharing with the representational capacity of multiple independent networks to reduce training time and increase final returns.

Related papers

• From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning [62.54484062185869]
  We introduce StepAgent, which utilizes step-wise reward to optimize the agent's reinforcement learning process. We propose implicit-reward and inverse reinforcement learning techniques to facilitate agent reflection and policy adjustment.
  arXiv  Detail & Related papers  (2024-11-06T10:35:11Z)
• Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning [14.01772209044574]
  We introduce emphKaleidoscope, a novel adaptive partial parameter sharing scheme. It promotes diversity among policy networks by encouraging discrepancy among these masks, without sacrificing the efficiencies of parameter sharing. We extend Kaleidoscope to critic ensembles in the context of actor-critic algorithms, which could help improve value estimations.
  arXiv  Detail & Related papers  (2024-10-11T05:22:54Z)
• MoS: Unleashing Parameter Efficiency of Low-Rank Adaptation with Mixture of Shards [35.163843138935455]
  The rapid scaling of large language models requires more lightweight finetuning methods to reduce the explosive GPU memory overhead. Our research highlights the indispensable role of differentiation in reversing the detrimental effects of pure sharing. We propose Mixture of Shards (MoS), incorporating both inter-layer and intra-layer sharing schemes, and integrating four nearly cost-free differentiation strategies.
  arXiv  Detail & Related papers  (2024-10-01T07:47:03Z)
• SHERL: Synthesizing High Accuracy and Efficient Memory for Resource-Limited Transfer Learning [63.93193829913252]
  We propose an innovative METL strategy called SHERL for resource-limited scenarios. In the early route, intermediate outputs are consolidated via an anti-redundancy operation. In the late route, utilizing minimal late pre-trained layers could alleviate the peak demand on memory overhead.
  arXiv  Detail & Related papers  (2024-07-10T10:22:35Z)
• PPS-QMIX: Periodically Parameter Sharing for Accelerating Convergence of Multi-Agent Reinforcement Learning [20.746383793882984]
  Training for multi-agent reinforcement learning(MARL) is a time-consuming process. One drawback is that strategy of each agent in MARL is independent but actually in cooperation. We propose three simple approaches called Average Sharing(A-PPS), Reward-Scalability Periodically and Partial Personalized Periodically.
  arXiv  Detail & Related papers  (2024-03-05T03:59:01Z)
• MELoRA: Mini-Ensemble Low-Rank Adapters for Parameter-Efficient Fine-Tuning [71.50432879573614]
  Low-rank adaptation (LoRA) is based on the idea that the adaptation process is intrinsically low-dimensional. We present MELoRA, a mini-ensemble low-rank adapters that uses fewer trainable parameters while maintaining a higher rank. Our experimental results show that, compared to LoRA, MELoRA achieves better performance with 8 times fewer trainable parameters on natural language understanding tasks and 36 times fewer trainable parameters on instruction following tasks.
  arXiv  Detail & Related papers  (2024-02-27T07:14:12Z)
• Dynamic Layer Tying for Parameter-Efficient Transformers [65.268245109828]
  We employ Reinforcement Learning to select layers during training and tie them together. This facilitates weight sharing, reduces the number of trainable parameters, and also serves as an effective regularization technique. In particular, the memory consumption during training is up to one order of magnitude less than the conventional training method.
  arXiv  Detail & Related papers  (2024-01-23T14:53:20Z)
• Adaptive parameter sharing for multi-agent reinforcement learning [16.861543418593044]
  We propose a novel parameter sharing method inspired by research pertaining to the brain in biology. It maps each type of agent to different regions within a shared network based on their identity, resulting in distinctworks. Our method can increase the diversity of strategies among different agents without additional training parameters.
  arXiv  Detail & Related papers  (2023-12-14T15:00:32Z)
• Parameter Sharing with Network Pruning for Scalable Multi-Agent Deep Reinforcement Learning [20.35644044703191]
  We propose a simple method that adopts structured pruning for a deep neural network to increase the representational capacity of the joint policy without introducing additional parameters. We evaluate the proposed method on several benchmark tasks, and numerical results show that the proposed method significantly outperforms other parameter-sharing methods.
  arXiv  Detail & Related papers  (2023-03-02T02:17:14Z)
• Efficient Feature Transformations for Discriminative and Generative Continual Learning [98.10425163678082]
  We propose a simple task-specific feature map transformation strategy for continual learning. Theses provide powerful flexibility for learning new tasks, achieved with minimal parameters added to the base architecture. We demonstrate the efficacy and efficiency of our method with an extensive set of experiments in discriminative (CIFAR-100 and ImageNet-1K) and generative sequences of tasks.
  arXiv  Detail & Related papers  (2021-03-25T01:48:14Z)
• Joint Parameter-and-Bandwidth Allocation for Improving the Efficiency of Partitioned Edge Learning [73.82875010696849]
  Machine learning algorithms are deployed at the network edge for training artificial intelligence (AI) models. This paper focuses on the novel joint design of parameter (computation load) allocation and bandwidth allocation.
  arXiv  Detail & Related papers  (2020-03-10T05:52:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.