paper-with-me

Papers

Pre-training with Synthetic Data Helps Offline Reinforcement Learning

2023-10-01 · Zecheng Wang, Che Wang, Zixuan Dong, Keith Ross

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.

📄 PDF Abstract BibTeX arXiv:2310.00771

Code (1)

victor-wang-902/synthetic-pretrain-rl 공식 구현 pytorch

Tasks

D4RLDeep Reinforcement LearningQ-Learningreinforcement-learningReinforcement Learning

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Adam 설명 없음
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

Efficient Offline Reinforcement Learning: The Critic is Critical

2024-06-19 · Adam Jelley, Trevor McInroe, Sam Devlin, Amos Storkey

Recent work has demonstrated both benefits and limitations from using supervised approaches (without temporal-difference learning) for offline reinforcement learning. While off-policy reinforcement learning provides a pr…

reinforcement-learningReinforcement Learning

PrivORL: Differentially Private Synthetic Dataset for Offline Reinforcement Learning

2025-12-08 · Chen Gong, Zheng Liu, Kecen Li, Tianhao Wang arxiv

Recently, offline reinforcement learning (RL) has become a popular RL paradigm. In offline RL, data providers share pre-collected datasets -- either as individual transitions or sequences of transitions forming trajector…

Reinforcement LearningOffline RL

Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data

2024-12-10 · Zhiyuan Zhou, Andy Peng, Qiyang Li, Sergey Levine 외

The modern paradigm in machine learning involves pre-training on diverse data, followed by task-specific fine-tuning. In reinforcement learning (RL), this translates to learning via offline RL on a diverse historical dat…

Offline RLReinforcement Learning (RL)

NeoRL: A Near Real-World Benchmark for Offline Reinforcement Learning

2021-02-01 · Rongjun Qin, Songyi Gao, Xingyuan Zhang, Zhen Xu 외

Offline reinforcement learning (RL) aims at learning a good policy from a batch of collected data, without extra interactions with the environment during training. However, current offline RL benchmarks commonly have a l…

Offline RLreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Behavior Estimation from Multi-Source Data for Offline Reinforcement Learning

2022-11-29 · Guoxi Zhang, Hisashi Kashima

Offline reinforcement learning (RL) have received rising interest due to its appealing data efficiency. The present study addresses behavior estimation, a task that lays the foundation of many offline RL algorithms. Beha…

Offline RLreinforcement-learningReinforcement LearningReinforcement Learning (RL)