Pith. sign in

REVIEW 2 cited by

Pre-training with Synthetic Data Helps Offline 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 2310.00771 v4 pith:P6YOQZ2Z submitted 2023-10-01 cs.AI cs.LG

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

Recently, it has been shown that for offline deep reinforcement learning (DRL), pre-training Decision Transformer with a large language corpus can improve downstream performance (Reid et al., 2022). A natural question to ask is whether this performance gain can only be achieved with language pre-training, or can be achieved with simpler pre-training schemes which do not involve language. In this paper, we first show that language is not essential for improved performance, and indeed pre-training with synthetic IID data for a small number of updates can match the performance gains from pre-training with a large language corpus; moreover, pre-training with data generated by a one-step Markov chain can further improve the performance. Inspired by these experimental results, we then consider pre-training Conservative Q-Learning (CQL), a popular offline DRL algorithm, which is Q-learning-based and typically employs a Multi-Layer Perceptron (MLP) backbone. Surprisingly, pre-training with simple synthetic data for a small number of updates can also improve CQL, providing consistent performance improvement on D4RL Gym locomotion datasets. The results of this paper not only illustrate the importance of pre-training for offline DRL but also show that the pre-training data can be synthetic and generated with remarkably simple mechanisms.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

  1. Transformers Pretrained on Procedural Data Contain Modular Structures for Algorithmic Reasoning

    cs.LG 2025-05 conditional novelty 6.0 of 10

    Different procedural pretraining tasks create complementary, transferable structures in a transformer's attention and MLP weights, and structures from different tasks can be combined into one initialization.

  2. Procedural Pretraining: Warming Up Language Models with Abstract Data

    cs.CL 2026-01 conditional novelty 5.0 of 10

    A short warm-up on procedural data (brackets, sorting, sets) makes language models more accurate and more data-efficient on language, code, and informal math.

Pith tools