Pith. sign in

REVIEW 6 cited by

Stabilizing Transformers for 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 1910.06764 v1 pith:ZTRCD5SI submitted 2019-10-13 cs.LG cs.AIstat.ML

Stabilizing Transformers for Reinforcement Learning

classification cs.LG cs.AIstat.ML
keywords learningarchitecturegtrxlmemoryperformancetransformerabilityarchitectural
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Owing to their ability to both effectively integrate information over long time horizons and scale to massive amounts of data, self-attention architectures have recently shown breakthrough success in natural language processing (NLP), achieving state-of-the-art results in domains such as language modeling and machine translation. Harnessing the transformer's ability to process long time horizons of information could provide a similar performance boost in partially observable reinforcement learning (RL) domains, but the large-scale transformers used in NLP have yet to be successfully applied to the RL setting. In this work we demonstrate that the standard transformer architecture is difficult to optimize, which was previously observed in the supervised learning setting but becomes especially pronounced with RL objectives. We propose architectural modifications that substantially improve the stability and learning speed of the original Transformer and XL variant. The proposed architecture, the Gated Transformer-XL (GTrXL), surpasses LSTMs on challenging memory environments and achieves state-of-the-art results on the multi-task DMLab-30 benchmark suite, exceeding the performance of an external memory architecture. We show that the GTrXL, trained using the same losses, has stability and performance that consistently matches or exceeds a competitive LSTM baseline, including on more reactive tasks where memory is less critical. GTrXL offers an easy-to-train, simple-to-implement but substantially more expressive architectural alternative to the standard multi-layer LSTM ubiquitously used for RL agents in partially observable environments.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 6 Pith papers

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

  1. Graph Transformers and Stabilized Reinforcement Learning for Large-Scale Dynamic Routing Modulation and Spectrum Allocation in Elastic Optical Networks

    cs.NI 2026-05 conditional novelty 7.0

    Graph transformer RL for dynamic RMSA supports up to 13% more traffic than benchmarks on networks up to 143 nodes and 362 links.

  2. Graph Transformers and Stabilized Reinforcement Learning for Large-Scale Dynamic Routing Modulation and Spectrum Allocation in Elastic Optical Networks

    cs.NI 2026-05 unverdicted novelty 7.0

    A graph transformer with RL stabilizations is the first to exceed benchmarks for dynamic RMSA, supporting up to 13% more traffic load on networks up to 143 nodes.

  3. Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads

    cs.LG 2024-01 conditional novelty 7.0

    Medusa augments LLMs with multiple decoding heads and tree-based attention to predict and verify several tokens in parallel, yielding 2.2-3.6x inference speedup via two fine-tuning regimes.

  4. Anticipatory Reinforcement Learning: From Generative Path-Laws to Distributional Value Functions

    cs.LG 2026-04 unverdicted novelty 6.0

    ARL lifts states into signature-augmented manifolds and employs self-consistent proxies of future path-laws to enable deterministic expected-return evaluation while preserving contraction mappings in jump-diffusion en...

  5. Gated Memory Policy

    cs.RO 2026-04 unverdicted novelty 5.0

    GMP selectively activates and represents memory via a gate and lightweight cross-attention, yielding 30.1% higher success on non-Markovian robotic tasks while staying competitive on Markovian ones.

  6. Belief-State RWKV for Reinforcement Learning under Partial Observability

    cs.LG 2026-04 unverdicted novelty 5.0

    Belief-state RWKV maintains an uncertainty-aware recurrent state for RL policies in partial observability and shows modest gains over standard recurrent baselines in a pilot with observation noise.