Pith. sign in

REVIEW 6 cited by

Mixtures of Experts Unlock Parameter Scaling for Deep RL

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2402.08609 v3 pith:YFE5TSVZ submitted 2024-02-13 cs.LG cs.AI

Johan Obando-Ceron , Ghada Sokar , Timon Willi , Clare Lyle , Jesse Farebrother , Jakob Foerster , Gintare Karolina Dziugaite , Doina Precup
show 1 more author
Pablo Samuel Castro
This is my paper · ORCID
classification cs.LGcs.AI
keywords scalinglawslearningmodelperformanceempiricalmodelsparameter
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The recent rapid progress in (self) supervised learning models is in large part predicted by empirical scaling laws: a model's performance scales proportionally to its size. Analogous scaling laws remain elusive for reinforcement learning domains, however, where increasing the parameter count of a model often hurts its final performance. In this paper, we demonstrate that incorporating Mixture-of-Expert (MoE) modules, and in particular Soft MoEs (Puigcerver et al., 2023), into value-based networks results in more parameter-scalable models, evidenced by substantial performance increases across a variety of training regimes and model sizes. This work thus provides strong empirical evidence towards developing scaling laws for reinforcement learning.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

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

  1. SCOPE and SCION: A Benchmark and an Auditable Reference Pipeline for Schema Induction and Fusion from Text

    cs.AI 2026-05 conditional novelty 6.0 of 10

    A 24-dataset benchmark for inducing schema graphs from raw text, plus an auditable LLM-based pipeline that reports the highest scores on the benchmark's four schema-similarity metrics.

  2. Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformer

    cs.LG 2025-05 conditional novelty 6.0 of 10

    M3DT combines a Decision Transformer with grouped, separately trained expert modules and a learned router, achieving better normalized scores than baselines across 10 to 160 multi-task RL tasks.

  3. Hadamax Encoding: Elevating Performance in Model-Free Atari

    cs.LG 2025-05 conditional novelty 6.0 of 10

    Hadamax, a Hadamard-product and max-pooling encoder, improves PQN's median human-normalized Atari-57 score by about 80% with no algorithmic changes.

  4. ReBRAC-v2: The Return of the King

    cs.LG 2026-08 conditional novelty 5.0 of 10

    A fixed-recipe offline RL method combining normalizing-flow actors, categorical critics, staged training, and test-time refinement beats recent flow-based baselines by 22.5 points averaged over ten OGBench categories.

  5. Cooperative Multi-UAV Navigation in Complex Environments via Systematic Multi-Agent Deep Reinforcement Learning

    cs.RO 2026-07 conditional novelty 5.0 of 10

    A modular MARL framework with local-optima override, hierarchical self-imitation cloning, dual-condition curriculum, and a structure-aware mixture-of-experts achieves 75% cooperative success on an unseen mixed maze in...

  6. Is Exploration or Optimization the Problem for Deep Reinforcement Learning?

    cs.LG 2025-08 reject novelty 4.0 of 10

    Deep RL agents' best experienced trajectories are 2-3 times better than their learned policy's average return, suggesting exploitation and optimization issues dominate exploration challenges.

Pith tools