Pith. sign in

REVIEW 3 cited by

The Dormant Neuron Phenomenon in Deep Reinforcement Learning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2302.12902 v2 pith:QKXTI7XI submitted 2023-02-24 cs.LG

classification cs.LG
keywords dormantlearningneuronsphenomenondeepdemonstratenetworkneuron
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In this work we identify the dormant neuron phenomenon in deep reinforcement learning, where an agent's network suffers from an increasing number of inactive neurons, thereby affecting network expressivity. We demonstrate the presence of this phenomenon across a variety of algorithms and environments, and highlight its effect on learning. To address this issue, we propose a simple and effective method (ReDo) that Recycles Dormant neurons throughout training. Our experiments demonstrate that ReDo maintains the expressive power of networks by reducing the number of dormant neurons and results in improved performance.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. How Should We Meta-Learn Reinforcement Learning Algorithms?

    cs.LG 2025-07 conditional novelty 6.0 of 10

    A systematic comparison of black-box evolution, neural and symbolic distillation, and LLM-based proposal for meta-learning RL algorithms yields practical recommendations: warm-started LLM proposal is sample-efficient,...

  2. Balancing Expressivity and Robustness: Constrained Rational Activations for Reinforcement Learning

    cs.LG 2025-07 conditional novelty 6.0 of 10

    A constrained rational activation with denominator degree one larger than numerator and no constant term stabilizes high-UTD continuous control, while trading off long-term plasticity.

  3. Continual-RL for Generalization in Autonomous Racing on the RoboRacer Platform

    cs.RO 2026-07 conditional novelty 5.0 of 10

    SAC plus Continual Backpropagation, trained only on real multi-track data, fine-tunes in ~15 minutes on an unseen lower-friction RoboRacer track and outperforms MAP and MPC.

Pith tools