Rethinking Transformers in Solving POMDPs

• URL: http://arxiv.org/abs/2405.17358v3
• Date: Thu, 30 May 2024 07:54:40 GMT
• Title: Rethinking Transformers in Solving POMDPs
• Authors: Chenhao Lu, Ruizhe Shi, Yuyao Liu, Kaizhe Hu, Simon S. Du, Huazhe Xu,
• Abstract summary: 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.
• Score: 47.14499685668683
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Sequential decision-making algorithms such as reinforcement learning (RL) in real-world scenarios inevitably face environments with partial observability. This paper scrutinizes the effectiveness of a popular architecture, namely Transformers, in Partially Observable Markov Decision Processes (POMDPs) and reveals its theoretical limitations. We establish that 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. This paper casts doubt on the prevalent belief in Transformers as sequence models for RL and proposes to introduce a point-wise recurrent structure. The Deep Linear Recurrent Unit (LRU) emerges as a well-suited alternative for Partially Observable RL, with empirical results highlighting the sub-optimal performance of the Transformer and considerable strength of LRU.

Related papers

• 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)
• A Survey on Transformers in Reinforcement Learning [66.23773284875843]
  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.
  arXiv  Detail & Related papers  (2023-01-08T14:04:26Z)
• 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)
• Your Transformer May Not be as Powerful as You Expect [88.11364619182773]
  We mathematically analyze the power of RPE-based Transformers regarding whether the model is capable of approximating any continuous sequence-to-sequence functions. We present a negative result by showing there exist continuous sequence-to-sequence functions that RPE-based Transformers cannot approximate no matter how deep and wide the neural network is. We develop a novel attention module, called Universal RPE-based (URPE) Attention, which satisfies the conditions.
  arXiv  Detail & Related papers  (2022-05-26T14:51:30Z)
• Decision Transformer: Reinforcement Learning via Sequence Modeling [102.86873656751489]
  We present a framework that abstracts Reinforcement Learning (RL) as a sequence modeling problem. We present Decision Transformer, an architecture that casts the problem of RL as conditional sequence modeling. Despite its simplicity, Decision Transformer matches or exceeds the performance of state-of-the-art offline RL baselines on Atari, OpenAI Gym, and Key-to-Door tasks.
  arXiv  Detail & Related papers  (2021-06-02T17:53:39Z)
• Bayesian Transformer Language Models for Speech Recognition [59.235405107295655]
  State-of-the-art neural language models (LMs) represented by Transformers are highly complex. This paper proposes a full Bayesian learning framework for Transformer LM estimation.
  arXiv  Detail & Related papers  (2021-02-09T10:55:27Z)
• 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.