The Dreamer agent provides various benefits of Model-Based Reinforcement Learning (MBRL) such as sample efficiency, reusable knowledge, and safe planning. However, its world model and policy networks inherit the limitations of recurrent neural networks and thus an important question is how an MBRL framework can benefit from the recent advances of transformers and what the challenges are in doing so. In this paper, we propose a transformer-based MBRL agent, called TransDreamer. We first introduce the Transformer State-Space Model, a world model that leverages a transformer for dynamics predictions. We then share this world model with a transformer-based policy network and obtain stability in training a transformer-based RL agent. In experiments, we apply the proposed model to 2D visual RL and 3D first-person visual RL tasks both requiring long-range memory access for memory-based reasoning. We show that the proposed model outperforms Dreamer in these complex tasks.
SiT: Symmetry-Invariant Transformers for Generalisation in Reinforcement Learning
RIKEN Center for Advanced Intelligence Project（理化学研究所高级智能项目中心）；Google DeepMind（谷歌DeepMind）；Graduate School of Information Science and Technology, Osaka University（大阪大学信息科学与技术研究生院）
Many real-world applications such as robotics provide hard constraints on power and compute that limit the viable model complexity of Reinforcement Learning (RL) agents. Similarly, in many distributed RL settings, acting is done on un-accelerated hardware such as CPUs, which likewise restricts model size to prevent intractable experiment run times. These "actor-latency" constrained settings present a major obstruction to the scaling up of model complexity that has recently been extremely successful in supervised learning. To be able to utilize large model capacity while still operating within …
TU Kaiserslautern（凯泽斯劳滕工业大学）；German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）
Spatial Transformer Networks (STN) can generate geometric transformations which modify input images to improve the classifier's performance. In this work, we combine the idea of STN with Reinforcement Learning (RL). To this end, we break the affine transformation down into a sequence of simple and discrete transformations. We formulate the task as a Markovian Decision Process (MDP) and use RL to solve this sequential decision-making problem. STN architectures learn the transformation parameters by minimizing the classification error and backpropagating the gradients through a sub-differentiabl…
Multi-Phase Spacecraft Trajectory Optimization via Transformer-Based Reinforcement Learning
Aeronautics & Astronautics, Massachusetts Institute of Technology（航空与宇航科学系，麻省理工学院）；Department of Computer Systems Engineering, Universidad Politécnica de Madrid（计算机系统工程系，马德里理工大学）
In this article, for the first time, we propose a transformer network-based reinforcement learning (RL) method for power distribution network (PDN) optimization of high bandwidth memory (HBM). The proposed method can provide an optimal decoupling capacitor (decap) design to maximize the reduction of PDN self- and transfer impedance seen at multiple ports. An attention-based transformer network is implemented to directly parameterize decap optimization policy. The optimality performance is significantly improved since the attention mechanism has powerful expression to explore massive combinator…
In-Context Reinforcement Learning From Suboptimal Historical Data
Department of Electrical and Computer Engineering, Duke University, Durham, US（电气与计算机工程系，杜克大学，达勒姆，美国）；Department of Biostatistics and Bioinformatics, Duke University, Durham, US（生物统计学与生物信息学系，杜克大学，达勒姆，美国）；Department of Statistics and Data Science, Yale University, New Haven, US（统计学与数据科学系，耶鲁大学，新 Haven，美国）
Two-Stage Feature Generation with Transformer and Reinforcement Learning
College of Computer Science and Technology, Jilin University（吉林大学计算机科学与技术学院）；Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University（教育部符号计算与知识工程重点实验室）；Department of Computer Science, Portland State University（波特兰州立大学计算机科学系）
Decision Mamba: Reinforcement Learning via Hybrid Selective Sequence Modeling
School of Artificial Intelligence, Jilin University（吉林大学人工智能学院）；Institute of High Performance Computing, A*STAR（新加坡高性能计算研究院（新加坡科技研究局））；Lehigh University（理海大学）
University of Glasgow（格拉斯哥大学）；Glasgow Caledonian University（格拉斯哥卡利多尼亚大学）
Life and physical sciences have always been quick to adopt the latest advances in machine learning to accelerate scientific discovery. Examples of this are cell segmentation or cancer detection. Nevertheless, these exceptional results are based on mining previously created datasets to discover patterns or trends. Recent advances in AI have been demonstrated in real-time scenarios like self-driving cars or playing video games. However, these new techniques have not seen widespread adoption in life or physical sciences because experimentation can be slow. To tackle this limitation, this work aim…
UC Berkeley（加州大学伯克利分校）；Facebook AI Research（脸书人工智能研究院）；Google Brain（谷歌大脑）
We introduce a framework that abstracts Reinforcement Learning (RL) as a sequence modeling problem. This allows us to draw upon the simplicity and scalability of the Transformer architecture, and associated advances in language modeling such as GPT-x and BERT. In particular, we present Decision Transformer, an architecture that casts the problem of RL as conditional sequence modeling. Unlike prior approaches to RL that fit value functions or compute policy gradients, Decision Transformer simply outputs the optimal actions by leveraging a causally masked Transformer. By conditioning an autoregr…
Khoury College of Computer Sciences（Khoury计算机科学学院）；Northeastern University（东北大学）
Real-world reinforcement learning tasks often involve some form of partial observability where the observations only give a partial or noisy view of the true state of the world. Such tasks typically require some form of memory, where the agent has access to multiple past observations, in order to perform well. One popular way to incorporate memory is by using a recurrent neural network to access the agent's history. However, recurrent neural networks in reinforcement learning are often fragile and difficult to train, susceptible to catastrophic forgetting and sometimes fail completely as a res…
We empirically investigate how pre-training on data of different modalities, such as language and vision, affects fine-tuning of Transformer-based models to Mujoco offline reinforcement learning tasks. Analysis of the internal representation reveals that the pre-trained Transformers acquire largely different representations before and after pre-training, but acquire less information of data in fine-tuning than the randomly initialized one. A closer look at the parameter changes of the pre-trained Transformers reveals that their parameters do not change that much and that the bad performance of…
Recent times have witnessed sharp improvements in reinforcement learning tasks using deep reinforcement learning techniques like Deep Q Networks, Policy Gradients, Actor Critic methods which are based on deep learning based models and back-propagation of gradients to train such models. An active area of research in reinforcement learning is about training agents to play complex video games, which so far has been something accomplished only by human intelligence. Some state of the art performances in video game playing using deep reinforcement learning are obtained by processing the sequence of…
Monash University（莫纳什大学）；Sun Yat-sen University（中山大学）；Dark Matter AI Inc.（暗物质人工智能公司）
Recent advances in multi-agent reinforcement learning have been largely limited in training one model from scratch for every new task. The limitation is due to the restricted model architecture related to fixed input and output dimensions. This hinders the experience accumulation and transfer of the learned agent over tasks with diverse levels of difficulty (e.g. 3 vs 3 or 5 vs 6 multi-agent games). In this paper, we make the first attempt to explore a universal multi-agent reinforcement learning pipeline, designing one single architecture to fit tasks with the requirement of different observa…
We propose SwitchTT, a multi-task extension to Trajectory Transformer but enhanced with two striking features: (i) exploiting a sparsely activated model to reduce computation cost in multi-task offline model learning and (ii) adopting a distributional trajectory value estimator that improves policy performance, especially in sparse reward settings. These two enhancements make SwitchTT suitable for solving multi-task offline reinforcement learning problems, where model capacity is critical for absorbing the vast quantities of knowledge available in the multi-task dataset. More specifically, Swi…
Reinforcement Learning (RL) can be considered as a sequence modeling task: given a sequence of past state-action-reward experiences, an agent predicts a sequence of next actions. In this work, we propose State-Action-Reward Transformer (StARformer) for visual RL, which explicitly models short-term state-action-reward representations (StAR-representations), essentially introducing a Markovian-like inductive bias to improve long-term modeling. Our approach first extracts StAR-representations by self-attending image state patches, action, and reward tokens within a short temporal window. These ar…
The StarCraft II Multi-Agent Challenge (SMAC) was created to be a challenging benchmark problem for cooperative multi-agent reinforcement learning (MARL). SMAC focuses exclusively on the problem of StarCraft micromanagement and assumes that each unit is controlled individually by a learning agent that acts independently and only possesses local information; centralized training is assumed to occur with decentralized execution (CTDE). To perform well in SMAC, MARL algorithms must handle the dual problems of multi-agent credit assignment and joint action evaluation. This paper introduces a new a…
Shanghai Jiaotong University（上海交通大学）；JD Explore Adacemy（京东探索研究院）；Washington University in St Louis（圣路易斯华盛顿大学）；University of Sydney（悉尼大学）
Transformer, originally devised for natural language processing, has also attested significant success in computer vision. Thanks to its super expressive power, researchers are investigating ways to deploy transformers to reinforcement learning (RL) and the transformer-based models have manifested their potential in representative RL benchmarks. In this paper, we collect and dissect recent advances on transforming RL by transformer (transformer-based RL or TRL), in order to explore its development trajectory and future trend. We group existing developments in two categories: architecture enhan…
Meta-learning is a line of research that develops the ability to leverage past experiences to efficiently solve new learning problems. Meta-Reinforcement Learning (meta-RL) methods demonstrate a capability to learn behaviors that efficiently acquire and exploit information in several meta-RL problems. In this context, the Alchemy benchmark has been proposed by Wang et al. [2021]. Alchemy features a rich structured latent space that is challenging for state-of-the-art model-free RL methods. These methods fail to learn to properly explore then exploit. We develop a model-based algorithm. We trai…
Transformer World Model for Sample Efficient Multi-Agent Reinforcement Learning
Artificial Intelligence Research Centre (CitAI), City St George’s, University of London（人工智能研究中心（CitAI）、圣乔治大学）；Oxford Institute for Energy Studies (OIES), University of Oxford（牛津能源研究所（OIES）、牛津大学）
