PRIME: Plasticity Recovery in Multi-Agent Environments for UAV-Assisted Emergency Communication Networks

• URL: http://arxiv.org/abs/2607.17922v1
• Date: Mon, 20 Jul 2026 13:19:58 GMT
• Title: PRIME: Plasticity Recovery in Multi-Agent Environments for UAV-Assisted Emergency Communication Networks
• Abstract summary: As objectives shift, neurons progressively fall dormant and the shared policy loses the capacity to learn.<n>We show that sustained non-stationarity damages this internal state directly.<n> PRIME improves interquartile mean return by 24.9% over MAPPO.
• Score: 5.059907627897051
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Most reinforcement learning controllers for these networks assume stationary conditions, and the few that handle change react to the external environment while leaving the network's internal state unexamined. We show that sustained non-stationarity damages this internal state directly: as objectives shift, neurons progressively fall dormant and the shared policy loses the capacity to learn. The obvious remedy, resetting dormant neurons, is unsafe under shared-parameter multi-agent training: many neurons that appear inactive are still receiving strong training gradients, and whether a neuron appears dormant depends on which agent's observations it processes. PRIME (Plasticity Recovery In Multi-agent Environments) therefore verifies both directions before intervening. Extending the bidirectional Silent Neuron framework to cooperative multi-agent reinforcement learning, it aggregates activation and gradient statistics over the full team batch, reads the backward signal from the gradient the training loss has already deposited , not from a hand-crafted proxy, and reinitializes only neurons that are simultaneously activation-dormant and gradient-silent. Useful representations are preserved while learning capacity is restored. On a phase-switching UAV emergency communication simulator, PRIME improves interquartile mean return by 24.9\% over MAPPO and holds dormant neuron fractions at 10--20\% versus 40--45\%; ablations attribute the gains to the gradient signal and team-level aggregation rather than to the specific reset operator. A dynamic regret bound shows that the perturbation cost scales with the small silent-subspace dimension rather than the full parameter count.

Related papers

• Calibrated Partial Resets: Preventing Policy Collapse in Continual Reinforcement Learning [3.1681974483553663]
  We propose Calibrated Partial Resets (CPR) to preserve plasticity without destabilizing training.<n>CPR avoids policy collapse over 400M training steps in SlipperyAnt.<n>CPR highlights utility-scaled reinitialization as a promising direction for continual learning.
  arXiv  Detail & Related papers  (2026-07-27T18:53:00Z)
• Human-AI Agent Interaction as a Neuroplastic Training Environment [3.8263925497663167]
  We observe that everyday agent interaction is an unrecognised neuroplastic training environment.<n>When a result disappoints, reactive patterns of impatience, perfectionism, frustration, and self-criticism are repeatedly evoked.<n>We propose that the same training environment can be engaged to the opposite effect.
  arXiv  Detail & Related papers  (2026-07-14T14:36:04Z)
• Sparse Inter-Layer Dependencies of Transformer FFN Neurons [32.00544060412007]
  We study whether the activation of an FFN neuron can be explained by a sparse set of preceding neuron activations and attention outputs.<n>We introduce a training-free attribution method that estimates the relative influence of upstream neurons and attention outputs on a target neuron's activation.
  arXiv  Detail & Related papers  (2026-07-13T15:04:50Z)
• Tiny Brains, Giant Impact: Uncovering the Keystone Neurons of LLM with Just a Few Prompts [57.98275914877019]
  We show that across a wide range of open-weight Transformers, a subset of neurons remains consistently highly activated during inference across tasks of multiple capability dimensions.<n>By probing along the cross-task activation strength, an extremely sparse subset is isolated, whose removal causes a collapse in model behavior.<n>Our analysis reveals that keystone neurons are a stable and intrinsic neuron subset of the model that is largely established during pretraining.
  arXiv  Detail & Related papers  (2026-05-24T03:31:07Z)
• Plasticity-Enhanced Multi-Agent Mixture of Experts for Dynamic Objective Adaptation in UAVs-Assisted Emergency Communication Networks [5.059907627897051]
  We propose plasticity enhanced multi-agent mixture of experts (PE-MAMoE)<n>PE-MAMoE equips each UAV with a sparsely gated mixture of experts actor whose router selects a single specialist per step.<n>We derive a dynamic regret bound showing the tracking error scales with both environment variation and cumulative noise energy.
  arXiv  Detail & Related papers  (2026-04-10T06:46:29Z)
• A Backpropagation-Free Feedback-Hebbian Network for Continual Learning Dynamics [0.0]
  We show that a compact feedback pathway trained with local plasticity can support regeneration and continual-learning--relevant dynamics.<n>Results show that a compact feedback pathway trained with local plasticity can support regeneration and continual-learning--relevant dynamics.
  arXiv  Detail & Related papers  (2026-01-11T03:25:38Z)
• Understanding and Minimising Outlier Features in Neural Network Training [33.980628229566555]
  Outlier Features (OFs) are neurons whose activation magnitudes significantly exceed the average over a neural network's (NN) width. We study how architectural and optimisation choices influence OFs, and provide practical insights to minimise OFs during training. We introduce a novel unnormalised transformer block, the Outlier Protected block, and present a previously unknown benefit of non-diagonal preconditioning optimisers.
  arXiv  Detail & Related papers  (2024-05-29T17:11:28Z)
• Contrastive-Signal-Dependent Plasticity: Self-Supervised Learning in Spiking Neural Circuits [61.94533459151743]
  This work addresses the challenge of designing neurobiologically-motivated schemes for adjusting the synapses of spiking networks. Our experimental simulations demonstrate a consistent advantage over other biologically-plausible approaches when training recurrent spiking networks.
  arXiv  Detail & Related papers  (2023-03-30T02:40:28Z)
• Learning Bayesian Sparse Networks with Full Experience Replay for Continual Learning [54.7584721943286]
  Continual Learning (CL) methods aim to enable machine learning models to learn new tasks without catastrophic forgetting of those that have been previously mastered. Existing CL approaches often keep a buffer of previously-seen samples, perform knowledge distillation, or use regularization techniques towards this goal. We propose to only activate and select sparse neurons for learning current and past tasks at any stage.
  arXiv  Detail & Related papers  (2022-02-21T13:25:03Z)
• Adaptive Rational Activations to Boost Deep Reinforcement Learning [68.10769262901003]
  We motivate why rationals are suitable for adaptable activation functions and why their inclusion into neural networks is crucial. We demonstrate that equipping popular algorithms with (recurrent-)rational activations leads to consistent improvements on Atari games.
  arXiv  Detail & Related papers  (2021-02-18T14:53:12Z)
• And/or trade-off in artificial neurons: impact on adversarial robustness [91.3755431537592]
  Presence of sufficient number of OR-like neurons in a network can lead to classification brittleness and increased vulnerability to adversarial attacks. We define AND-like neurons and propose measures to increase their proportion in the network. Experimental results on the MNIST dataset suggest that our approach holds promise as a direction for further exploration.
  arXiv  Detail & Related papers  (2021-02-15T08:19:05Z)
• Automatic Recall Machines: Internal Replay, Continual Learning and the Brain [104.38824285741248]
  Replay in neural networks involves training on sequential data with memorized samples, which counteracts forgetting of previous behavior caused by non-stationarity. We present a method where these auxiliary samples are generated on the fly, given only the model that is being trained for the assessed objective. Instead the implicit memory of learned samples within the assessed model itself is exploited.
  arXiv  Detail & Related papers  (2020-06-22T15:07:06Z)
• Feature Purification: How Adversarial Training Performs Robust Deep Learning [66.05472746340142]
  We show a principle that we call Feature Purification, where we show one of the causes of the existence of adversarial examples is the accumulation of certain small dense mixtures in the hidden weights during the training process of a neural network. We present both experiments on the CIFAR-10 dataset to illustrate this principle, and a theoretical result proving that for certain natural classification tasks, training a two-layer neural network with ReLU activation using randomly gradient descent indeed this principle.
  arXiv  Detail & Related papers  (2020-05-20T16:56:08Z)

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.