paper-with-me

Papers

Reinformer: Max-Return Sequence Modeling for Offline RL

2024-05-14 · Zifeng Zhuang, Dengyun Peng, Jinxin Liu, Ziqi Zhang, Donglin Wang

As a data-driven paradigm, offline reinforcement learning (RL) has been formulated as sequence modeling that conditions on the hindsight information including returns, goal or future trajectory. Although promising, this supervised paradigm overlooks the core objective of RL that maximizes the return. This overlook directly leads to the lack of trajectory stitching capability that affects the sequence model learning from sub-optimal data. In this work, we introduce the concept of max-return sequence modeling which integrates the goal of maximizing returns into existing sequence models. We propose Reinforced Transformer (Reinformer), indicating the sequence model is reinforced by the RL objective. Reinformer additionally incorporates the objective of maximizing returns in the training phase, aiming to predict the maximum future return within the distribution. During inference, this in-distribution maximum return will guide the selection of optimal actions. Empirically, Reinformer is competitive with classical RL methods on the D4RL benchmark and outperforms state-of-the-art sequence model particularly in trajectory stitching ability. Code is public at https://github.com/Dragon-Zhuang/Reinformer.

📄 PDF Abstract BibTeX arXiv:2405.08740

Code (1)

dragon-zhuang/reinformer 공식 구현 pytorch

Tasks

D4RLOffline RLReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head 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…
Position-Wise Feed-Forward Layer 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
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…
Residual Connection 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Similar Papers 제목 키워드 기반

Hybrid Sequence Modeling and Reinforced Verification for Controllable Target-Conditioned Decision Making

2025-08-22 · Yue Pei, Hongming Zhang, Chao Gao, Martin Müller 외 arxiv

Target-conditioned sequence models provide a simple interface for controllable offline decision making, but the requested target return can be an unreliable control signal, especially when the target return lies in under…

Decision Making

SaFormer: A Conditional Sequence Modeling Approach to Offline Safe Reinforcement Learning

2023-01-28 · Qin Zhang, Linrui Zhang, Haoran Xu, Li Shen 외

Offline safe RL is of great practical relevance for deploying agents in real-world applications. However, acquiring constraint-satisfying policies from the fixed dataset is non-trivial for conventional approaches. Even w…

reinforcement-learningReinforcement Learning (RL)Safe Reinforcement Learning

Conditional Sequence Modeling for Safe Reinforcement Learning

2026-02-09 · Wensong Bai, Chao Zhang, Qihang Xu, Chufan Chen 외 arxiv

Offline safe reinforcement learning (RL) aims to learn policies from a fixed dataset while maximizing performance under cumulative cost constraints. In practice, deployment requirements often vary across scenarios, neces…

Reinforcement Learning

In-Dataset Trajectory Return Regularization for Offline Preference-based Reinforcement Learning

2024-12-12 · Songjun Tu, Jingbo Sun, Qichao Zhang, Yaocheng Zhang 외

Offline preference-based reinforcement learning (PbRL) typically operates in two phases: first, use human preferences to learn a reward model and annotate rewards for a reward-free offline dataset; second, learn a policy…

Offline RL

Q-value Regularized Decision ConvFormer for Offline Reinforcement Learning

2024-09-12 · Teng Yan, Zhendong Ruan, Yaobang Cai, Yu Han 외

As a data-driven paradigm, offline reinforcement learning (Offline RL) has been formulated as sequence modeling, where the Decision Transformer (DT) has demonstrated exceptional capabilities. Unlike previous reinforcemen…

D4RLOffline RLreinforcement-learningReinforcement Learning