Transformer in Transformer as Backbone for Deep Reinforcement Learning

• URL: http://arxiv.org/abs/2212.14538v2
• Date: Tue, 3 Jan 2023 06:51:22 GMT
• Title: Transformer in Transformer as Backbone for Deep Reinforcement Learning
• Authors: Hangyu Mao, Rui Zhao, Hao Chen, Jianye Hao, Yiqun Chen, Dong Li, Junge Zhang, Zhen Xiao
• Abstract summary: We propose to design emphpure Transformer-based networks for deep RL. The Transformer in Transformer (TIT) backbone is proposed, which cascades two Transformers in a very natural way. Experiments show that TIT can achieve satisfactory performance in different settings consistently.
• Score: 43.354375917223656
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Designing better deep networks and better reinforcement learning (RL) algorithms are both important for deep RL. This work focuses on the former. Previous methods build the network with several modules like CNN, LSTM and Attention. Recent methods combine the Transformer with these modules for better performance. However, it requires tedious optimization skills to train a network composed of mixed modules, making these methods inconvenient to be used in practice. In this paper, we propose to design \emph{pure Transformer-based networks} for deep RL, aiming at providing off-the-shelf backbones for both the online and offline settings. Specifically, the Transformer in Transformer (TIT) backbone is proposed, which cascades two Transformers in a very natural way: the inner one is used to process a single observation, while the outer one is responsible for processing the observation history; combining both is expected to extract spatial-temporal representations for good decision-making. Experiments show that TIT can achieve satisfactory performance in different settings consistently.

Related papers

• Heterogeneous Federated Learning with Splited Language Model [22.65325348176366]
  Federated Split Learning (FSL) is a promising distributed learning paradigm in practice. In this paper, we harness Pre-trained Image Transformers (PITs) as the initial model, coined FedV, to accelerate the training process and improve model robustness. We are the first to provide a systematic evaluation of FSL methods with PITs in real-world datasets, different partial device participations, and heterogeneous data splits.
  arXiv  Detail & Related papers  (2024-03-24T07:33:08Z)
• PDiT: Interleaving Perception and Decision-making Transformers for Deep Reinforcement Learning [27.128220336919195]
  Perception and Decision-making Interleaving Transformer (PDiT) network is proposed. Experiments show that PDiT can not only achieve superior performance than strong baselines but also extractable feature representations.
  arXiv  Detail & Related papers  (2023-12-26T03:07:10Z)
• Transformer Fusion with Optimal Transport [25.022849817421964]
  Fusion is a technique for merging multiple independently-trained neural networks in order to combine their capabilities. This paper presents a systematic approach for fusing two or more transformer-based networks exploiting Optimal Transport to (soft-)align the various architectural components.
  arXiv  Detail & Related papers  (2023-10-09T13:40:31Z)
• Supervised Pretraining Can Learn In-Context Reinforcement Learning [96.62869749926415]
  In this paper, we study the in-context learning capabilities of transformers in decision-making problems. We introduce and study Decision-Pretrained Transformer (DPT), a supervised pretraining method where the transformer predicts an optimal action. We find that the pretrained transformer can be used to solve a range of RL problems in-context, exhibiting both exploration online and conservatism offline.
  arXiv  Detail & Related papers  (2023-06-26T17:58:50Z)
• Emergent Agentic Transformer from Chain of Hindsight Experience [96.56164427726203]
  We show that a simple transformer-based model performs competitively with both temporal-difference and imitation-learning-based approaches. This is the first time that a simple transformer-based model performs competitively with both temporal-difference and imitation-learning-based approaches.
  arXiv  Detail & Related papers  (2023-05-26T00:43:02Z)
• Deep Transformers without Shortcuts: Modifying Self-attention for Faithful Signal Propagation [105.22961467028234]
  Skip connections and normalisation layers are ubiquitous for the training of Deep Neural Networks (DNNs) Recent approaches such as Deep Kernel Shaping have made progress towards reducing our reliance on them. But these approaches are incompatible with the self-attention layers present in transformers.
  arXiv  Detail & Related papers  (2023-02-20T21:26:25Z)
• On Transforming Reinforcement Learning by Transformer: The Development Trajectory [97.79247023389445]
  Transformer, originally devised for natural language processing, has also attested significant success in computer vision. We group existing developments in two categories: architecture enhancement and trajectory optimization. We examine the main applications of TRL in robotic manipulation, text-based games, navigation and autonomous driving.
  arXiv  Detail & Related papers  (2022-12-29T03:15:59Z)
• Video Super-Resolution Transformer [85.11270760456826]
  Video super-resolution (VSR), with the aim to restore a high-resolution video from its corresponding low-resolution version, is a spatial-temporal sequence prediction problem. Recently, Transformer has been gaining popularity due to its parallel computing ability for sequence-to-sequence modeling. In this paper, we present a spatial-temporal convolutional self-attention layer with a theoretical understanding to exploit the locality information.
  arXiv  Detail & Related papers  (2021-06-12T20:00:32Z)
• TransReID: Transformer-based Object Re-Identification [20.02035310635418]
  Vision Transformer (ViT) is a pure transformer-based model for the object re-identification (ReID) task. With several adaptations, a strong baseline ViT-BoT is constructed with ViT as backbone. We propose a pure-transformer framework dubbed as TransReID, which is the first work to use a pure Transformer for ReID research.
  arXiv  Detail & Related papers  (2021-02-08T17:33:59Z)
• Stabilizing Transformer-Based Action Sequence Generation For Q-Learning [5.707122938235432]
  The goal is a simple Transformer-based Deep Q-Learning method that is stable over several environments. The proposed method can match the performance of classic Q-learning on control environments while showing potential on some selected Atari benchmarks.
  arXiv  Detail & Related papers  (2020-10-23T22:55:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.