A Survey on Transformers in Reinforcement Learning
- URL: http://arxiv.org/abs/2301.03044v3
- Date: Wed, 20 Sep 2023 21:12:31 GMT
- Title: A Survey on Transformers in Reinforcement Learning
- Authors: Wenzhe Li, Hao Luo, Zichuan Lin, Chongjie Zhang, Zongqing Lu, Deheng
Ye
- Abstract summary: Transformer has been considered the dominating neural architecture in NLP and CV, mostly under supervised settings.
Recently, a similar surge of using Transformers has appeared in the domain of reinforcement learning (RL), but it is faced with unique design choices and challenges brought by the nature of RL.
This paper systematically reviews motivations and progress on using Transformers in RL, provide a taxonomy on existing works, discuss each sub-field, and summarize future prospects.
- Score: 66.23773284875843
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Transformer has been considered the dominating neural architecture in NLP and
CV, mostly under supervised settings. Recently, a similar surge of using
Transformers has appeared in the domain of reinforcement learning (RL), but it
is faced with unique design choices and challenges brought by the nature of RL.
However, the evolution of Transformers in RL has not yet been well unraveled.
In this paper, we seek to systematically review motivations and progress on
using Transformers in RL, provide a taxonomy on existing works, discuss each
sub-field, and summarize future prospects.
Related papers
- Rethinking Transformers in Solving POMDPs [47.14499685668683]
This paper scrutinizes the effectiveness of a popular architecture, namely Transformers, in Partially Observable Markov Decision Processes (POMDPs)
Regular languages, which Transformers struggle to model, are reducible to POMDPs.
This poses a significant challenge for Transformers in learning POMDP-specific inductive biases, due to their lack of inherent recurrence found in other models like RNNs.
arXiv Detail & Related papers (2024-05-27T17:02:35Z) - Introduction to Transformers: an NLP Perspective [59.0241868728732]
We introduce basic concepts of Transformers and present key techniques that form the recent advances of these models.
This includes a description of the standard Transformer architecture, a series of model refinements, and common applications.
arXiv Detail & Related papers (2023-11-29T13:51:04Z) - Transformers in Reinforcement Learning: A Survey [7.622978576824539]
Transformers have impacted domains like natural language processing, computer vision, and robotics, where they improve performance compared to other neural networks.
This survey explores how transformers are used in reinforcement learning (RL), where they are seen as a promising solution for addressing challenges such as unstable training, credit assignment, lack of interpretability, and partial observability.
arXiv Detail & Related papers (2023-07-12T07:51:12Z) - 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) - 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) - 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) - Applying the Transformer to Character-level Transduction [68.91664610425114]
The transformer has been shown to outperform recurrent neural network-based sequence-to-sequence models in various word-level NLP tasks.
We show that with a large enough batch size, the transformer does indeed outperform recurrent models for character-level tasks.
arXiv Detail & Related papers (2020-05-20T17:25:43Z) - Adaptive Transformers in RL [6.292138336765965]
Recent developments in Transformers have opened new areas of research in partially observable reinforcement learning tasks.
Results from late 2019 showed that Transformers are able to outperform LSTMs on both memory intense and reactive tasks.
arXiv Detail & Related papers (2020-04-08T01:03:10Z)
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.