We are interested in how to design reinforcement learning agents that provably reduce the sample complexity for learning new tasks by transferring knowledge from previously-solved ones. The availability of solutions to related problems poses a fundamental trade-off: whether to seek policies that are expected to achieve high (yet sub-optimal) performance in the new task immediately or whether to seek information to quickly identify an optimal solution, potentially at the cost of poor initial behavior. In this work, we focus on the second objective when the agent has access to a generative model of state-action pairs. First, given a set of solved tasks containing an approximation of the target one, we design an algorithm that quickly identifies an accurate solution by seeking the state-action pairs that are most informative for this purpose. We derive PAC bounds on its sample complexity which clearly demonstrate the benefits of using this kind of prior knowledge. Then, we show how to learn these approximate tasks sequentially by reducing our transfer setting to a hidden Markov model and employing spectral methods to recover its parameters. Finally, we empirically verify our theoretical findings in simple simulated domains.
DQN (Deep Q-Network) is a method to perform Q-learning for reinforcement learning using deep neural networks. DQNs require a large buffer and batch processing for an experience replay and rely on a backpropagation based iterative optimization, making them difficult to be implemented on resource-limited edge devices. In this paper, we propose a lightweight on-device reinforcement learning approach for low-cost FPGA devices. It exploits a recently proposed neural-network based on-device learning approach that does not rely on the backpropagation method but uses OS-ELM (Online Sequential Extreme …
CSIRO’s Data61（澳大利亚联邦科学与工业研究组织数据61研究所）；CSIRO’s Land and Water（澳大利亚联邦科学与工业研究组织土地与水研究所）
Bayesian approaches developed to solve the optimal design of sequential experiments are mathematically elegant but computationally challenging. Recently, techniques using amortization have been proposed to make these Bayesian approaches practical, by training a parameterized policy that proposes designs efficiently at deployment time. However, these methods may not sufficiently explore the design space, require access to a differentiable probabilistic model and can only optimize over continuous design spaces. Here, we address these limitations by showing that the problem of optimizing policies…
Global Autoregressive Models (GAMs) are a recent proposal [Parshakova et al., CoNLL 2019] for exploiting global properties of sequences for data-efficient learning of seq2seq models. In the first phase of training, an Energy-Based model (EBM) over sequences is derived. This EBM has high representational power, but is unnormalized and cannot be directly exploited for sampling. To address this issue [Parshakova et al., CoNLL 2019] proposes a distillation technique, which can only be applied under limited conditions. By relating this problem to Policy Gradient techniques in RL, but in a \emph{dis…
Molecular geometry prediction of flexible molecules, or conformer search, is a long-standing challenge in computational chemistry. This task is of great importance for predicting structure-activity relationships for a wide variety of substances ranging from biomolecules to ubiquitous materials. Substantial computational resources are invested in Monte Carlo and Molecular Dynamics methods to generate diverse and representative conformer sets for medium to large molecules, which are yet intractable to chemoinformatic conformer search methods. We present TorsionNet, an efficient sequential confor…
One of the most interesting application scenarios in anomaly detection is when sequential data are targeted. For example, in a safety-critical environment, it is crucial to have an automatic detection system to screen the streaming data gathered by monitoring sensors and to report abnormal observations if detected in real-time. Oftentimes, stakes are much higher when these potential anomalies are intentional or goal-oriented. We propose an end-to-end framework for sequential anomaly detection using inverse reinforcement learning (IRL), whose objective is to determine the decision-making agent'…
We present a novel, alternative framework for learning generative models with goal-conditioned reinforcement learning. We define two agents, a goal conditioned agent (GC-agent) and a supervised agent (S-agent). Given a user-input initial state, the GC-agent learns to reconstruct the training set. In this context, elements in the training set are the goals. During training, the S-agent learns to imitate the GC-agent while remaining agnostic of the goals. At inference we generate new samples with the S-agent. Following a similar route as in variational auto-encoders, we derive an upper bound on …
Sequential Knockoffs for Variable Selection in Reinforcement Learning
London School of Economics and Political Science（伦敦政治经济学院）；University of California, Irvine（加州大学欧文分校）；George Washington University（乔治华盛顿大学）；Duke University（杜克大学）
PyCFRL: A Python library for counterfactually fair offline reinforcement learning via sequential data preprocessing
Department of Statistics, University of Michigan, USA（统计学系，密歇根大学）；Department of Biostatistics, University of Michigan, USA（生物统计学系，密歇根大学）；Department of Statistics, London School of Economics, UK（统计学系，伦敦经济学院）；Department of Health Behavior and Health Equity, School of Public Health, University of Michigan, USA（健康行为与健康公平系，公共卫生学院，密歇根大学）
Our research is focused on understanding and applying biological memory transfers to new AI systems that can fundamentally improve their performance, throughout their fielded lifetime experience. We leverage current understanding of biological memory transfer to arrive at AI algorithms for memory consolidation and replay. In this paper, we propose the use of generative memory that can be recalled in batch samples to train a multi-task agent in a pseudo-rehearsal manner. We show results motivating the need for task-agnostic separation of latent space for the generative memory to address issues …
Indian Institute of Technology Madras（印度理工学院马德拉斯分校）
Exploration in multi-task reinforcement learning is critical in training agents to deduce the underlying MDP. Many of the existing exploration frameworks such as $E^3$, $R_{max}$, Thompson sampling assume a single stationary MDP and are not suitable for system identification in the multi-task setting. We present a novel method to facilitate exploration in multi-task reinforcement learning using deep generative models. We supplement our method with a low dimensional energy model to learn the underlying MDP distribution and provide a resilient and adaptive exploration signal to the agent. We eva…
This paper proposes a novel scheme for the watermarking of Deep Reinforcement Learning (DRL) policies. This scheme provides a mechanism for the integration of a unique identifier within the policy in the form of its response to a designated sequence of state transitions, while incurring minimal impact on the nominal performance of the policy. The applications of this watermarking scheme include detection of unauthorized replications of proprietary policies, as well as enabling the graceful interruption or termination of DRL activities by authorized entities. We demonstrate the feasibility of o…
Systems Innovation, Faculty of Engineering, The University of Tokyo（东京大学工学部系统创新）
Bayesian experimental design (BED) has been used as a method for conducting efficient experiments based on Bayesian inference. The existing methods, however, mostly focus on maximizing the expected information gain (EIG); the cost of experiments and sample efficiency are often not taken into account. In order to address this issue and enhance practical applicability of BED, we provide a new approach Sequential Experimental Design via Reinforcement Learning to construct BED in a sequential manner by applying reinforcement learning in this paper. Here, reinforcement learning is a branch of machi…
Reinforcement learning has seen great advancements in the past five years. The successful introduction of deep learning in place of more traditional methods allowed reinforcement learning to scale to very complex domains achieving super-human performance in environments like the game of Go or numerous video games. Despite great successes in multiple domains, these new methods suffer from their own issues that make them often inapplicable to the real world problems. Extreme lack of data efficiency, together with huge variance and difficulty in enforcing safety constraints, is one of the three m…
We consider model-based reinforcement learning (MBRL) in 2-agent, high-fidelity continuous control problems -- an important domain for robots interacting with other agents in the same workspace. For non-trivial dynamical systems, MBRL typically suffers from accumulating errors. Several recent studies have addressed this problem by learning latent variable models for trajectory segments and optimizing over behavior in the latent space. In this work, we investigate whether this approach can be extended to 2-agent competitive and cooperative settings. The fundamental challenge is how to learn mod…
There are great interests as well as many challenges in applying reinforcement learning (RL) to recommendation systems. In this setting, an online user is the environment; neither the reward function nor the environment dynamics are clearly defined, making the application of RL challenging. In this paper, we propose a novel model-based reinforcement learning framework for recommendation systems, where we develop a generative adversarial network to imitate user behavior dynamics and learn her reward function. Using this user model as the simulation environment, we develop a novel Cascading DQN …
We introduce the use of reinforcement learning for indirect mechanisms, working with the existing class of sequential price mechanisms, which generalizes both serial dictatorship and posted price mechanisms and essentially characterizes all strongly obviously strategyproof mechanisms. Learning an optimal mechanism within this class forms a partially-observable Markov decision process. We provide rigorous conditions for when this class of mechanisms is more powerful than simpler static mechanisms, for sufficiency or insufficiency of observation statistics for learning, and for the necessity of …
School of Electrical Engineering, KAIST（韩国科学技术院电气工程学院）
This paper proposes a new sequential model learning architecture to solve partially observable Markov decision problems. Rather than compressing sequential information at every timestep as in conventional recurrent neural network-based methods, the proposed architecture generates a latent variable in each data block with a length of multiple timesteps and passes the most relevant information to the next block for policy optimization. The proposed blockwise sequential model is implemented based on self-attention, making the model capable of detailed sequential learning in partial observable set…
There are over 15 distinct communities that work in the general area of sequential decisions and information, often referred to as decisions under uncertainty or stochastic optimization. We focus on two of the most important fields: stochastic optimal control, with its roots in deterministic optimal control, and reinforcement learning, with its roots in Markov decision processes. Building on prior work, we describe a unified framework that covers all 15 different communities, and note the strong parallels with the modeling framework of stochastic optimal control. By contrast, we make the case …
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…
A key challenge in model-based reinforcement learning (RL) is to synthesize computationally efficient and accurate environment models. We show that carefully designed generative models that learn and operate on compact state representations, so-called state-space models, substantially reduce the computational costs for predicting outcomes of sequences of actions. Extensive experiments establish that state-space models accurately capture the dynamics of Atari games from the Arcade Learning Environment from raw pixels. The computational speed-up of state-space models while maintaining high accur…
Rochester Institute of Technology（罗切斯特理工学院）；Pennsylvania State University（宾夕法尼亚州立大学）
In humans, perceptual awareness facilitates the fast recognition and extraction of information from sensory input. This awareness largely depends on how the human agent interacts with the environment. In this work, we propose active neural generative coding, a computational framework for learning action-driven generative models without backpropagation of errors (backprop) in dynamic environments. Specifically, we develop an intelligent agent that operates even with sparse rewards, drawing inspiration from the cognitive theory of planning as inference. We demonstrate on several simple control p…
Media and Data Science Research Lab, Adobe（Adobe媒体与数据科学研究实验室）；IIT Kharagpur, India（印度理工学院卡格拉普尔分校）
In social dilemma situations, individual rationality leads to sub-optimal group outcomes. Several human engagements can be modeled as a sequential (multi-step) social dilemmas. However, in contrast to humans, Deep Reinforcement Learning agents trained to optimize individual rewards in sequential social dilemmas converge to selfish, mutually harmful behavior. We introduce a status-quo loss (SQLoss) that encourages an agent to stick to the status quo, rather than repeatedly changing its policy. We show how agents trained with SQLoss evolve cooperative behavior in several social dilemma matrix ga…
In this work, we investigate the properties of data that cause popular representation learning approaches to fail. In particular, we find that in environments where states do not significantly overlap, variational autoencoders (VAEs) fail to learn useful features. We demonstrate this failure in a simple gridworld domain, and then provide a solution in the form of metric learning. However, metric learning requires supervision in the form of a distance function, which is absent in reinforcement learning. To overcome this, we leverage the sequential nature of states in a replay buffer to approxim…
We present RLSS: a reinforcement learning algorithm for sequential scene generation. This is based on employing the proximal policy optimization (PPO) algorithm for generative problems. In particular, we consider how to effectively reduce the action space by including a greedy search algorithm in the learning process. Our experiments demonstrate that our method converges for a relatively large number of actions and learns to generate scenes with predefined design objectives. This approach is placing objects iteratively in the virtual scene. In each step, the network chooses which objects to pl…
Sequential Design of Genetic Circuits Under Uncertainty With Reinforcement Learning
School of Informatics, The University of Edinburgh（爱丁堡大学信息学院）；School of Informatics（信息学院）；School of Biological Sciences, The University of Edinburgh（爱丁堡大学生物科学学院）
Tencent AI Lab（腾讯人工智能实验室）；The Pennsylvania State University（宾夕法尼亚州立大学）
Offline reinforcement learning (RL) tries to learn the near-optimal policy with recorded offline experience without online exploration. Current offline RL research includes: 1) generative modeling, i.e., approximating a policy using fixed data; and 2) learning the state-action value function. While most research focuses on the state-action function part through reducing the bootstrapping error in value function approximation induced by the distribution shift of training data, the effects of error propagation in generative modeling have been neglected. In this paper, we analyze the error in gen…
School of Computer Science, McGill University（麦吉尔大学计算机科学学院）；Department of Electrical, Computer, and Software Engineering, McGill University（麦吉尔大学电气、计算机与软件工程系）
Reinforcement learning has shown promise in learning policies that can solve complex problems. However, manually specifying a good reward function can be difficult, especially for intricate tasks. Inverse reinforcement learning offers a useful paradigm to learn the underlying reward function directly from expert demonstrations. Yet in reality, the corpus of demonstrations may contain trajectories arising from a diverse set of underlying reward functions rather than a single one. Thus, in inverse reinforcement learning, it is useful to consider such a decomposition. The options framework in rei…
In offline reinforcement learning, weighted regression is a common method to ensure the learned policy stays close to the behavior policy and to prevent selecting out-of-sample actions. In this work, we show that due to the limited distributional expressivity of policy models, previous methods might still select unseen actions during training, which deviates from their initial motivation. To address this problem, we adopt a generative approach by decoupling the learned policy into two parts: an expressive generative behavior model and an action evaluation model. The key insight is that such de…
Recent years have seen a significant amount of interests in Sequential Recommendation (SR), which aims to understand and model the sequential user behaviors and the interactions between users and items over time. Surprisingly, despite the huge success Sequential Recommendation has achieved, there is little study on Sequential Search (SS), a twin learning task that takes into account a user's current and past search queries, in addition to behavior on historical query sessions. The SS learning task is even more important than the counterpart SR task for most of E-commence companies due to its m…
University of Miami（迈阿密大学）；New York University（纽约大学）；Alibaba Group（阿里巴巴集团）；Carnegie Mellon University（卡内基梅隆大学）
We utilize an offline reinforcement learning (RL) model for sequential targeted promotion in the presence of budget constraints in a real-world business environment. In our application, the mobile app aims to boost customer retention by sending cash bonuses to customers and control the costs of such cash bonuses during each time period. To achieve the multi-task goal, we propose the Budget Constrained Reinforcement Learning for Sequential Promotion (BCRLSP) framework to determine the value of cash bonuses to be sent to users. We first find out the target policy and the associated Q-values that…
Vector Institute for Artificial Intelligence（向量人工智能研究所）；University of Guelph（圭尔夫大学）
Although machine learning (ML) has been successful in automating various software engineering needs, software testing still remains a highly challenging topic. In this paper, we aim to improve the generative testing of software by directly augmenting the random number generator (RNG) with a deep reinforcement learning (RL) agent using an efficient, automatically extractable state representation of the software under test. Using the Cosmos SDK as the testbed, we show that the proposed DeepRNG framework provides a statistically significant improvement to the testing of the highly complex softwar…
University of Oxford（牛津大学）；Bartlett School of Architecture, UCL（伦敦大学学院巴特莱特建筑学院）
With this work, we investigate the use of Reinforcement Learning (RL) for the generation of spatial assemblies, by combining ideas from Procedural Generation algorithms (Wave Function Collapse algorithm (WFC)) and RL for Game Solving. WFC is a Generative Design algorithm, inspired by Constraint Solving. In WFC, one defines a set of tiles/blocks and constraints and the algorithm generates an assembly that satisfies these constraints. Casting the problem of generation of spatial assemblies as a Markov Decision Process whose states transitions are defined by WFC, we propose an algorithm that uses…
Revisiting Generative Policies: A Simpler Reinforcement Learning Algorithmic Perspective
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Xi’an Jiaotong University（西安交通大学）；SenseTime Research（商汤科技研究院）；Peking University（北京大学）；The Chinese University of Hong Kong（香港中文大学）
University of Toronto Robotics Institute（多伦多大学机器人研究所）；Vector Institute（向量研究所）；Montreal Institute of Learning Algorithms (MILA)（蒙特利尔学习算法研究所）；McGill University（麦吉尔大学）
The potential benefits of model-free reinforcement learning to real robotics systems are limited by its uninformed exploration that leads to slow convergence, lack of data-efficiency, and unnecessary interactions with the environment. To address these drawbacks we propose a method that combines reinforcement and imitation learning by shaping the reward function with a state-and-action-dependent potential that is trained from demonstration data, using a generative model. We show that this accelerates policy learning by specifying high-value areas of the state and action space that are worth exp…
Matrix games like Prisoner's Dilemma have guided research on social dilemmas for decades. However, they necessarily treat the choice to cooperate or defect as an atomic action. In real-world social dilemmas these choices are temporally extended. Cooperativeness is a property that applies to policies, not elementary actions. We introduce sequential social dilemmas that share the mixed incentive structure of matrix game social dilemmas but also require agents to learn policies that implement their strategic intentions. We analyze the dynamics of policies learned by multiple self-interested indep…
Neural networks can achieve excellent results in a wide variety of applications. However, when they attempt to sequentially learn, they tend to learn the new task while catastrophically forgetting previous ones. We propose a model that overcomes catastrophic forgetting in sequential reinforcement learning by combining ideas from continual learning in both the image classification domain and the reinforcement learning domain. This model features a dual memory system which separates continual learning from reinforcement learning and a pseudo-rehearsal system that "recalls" items representative o…
Hajim School of Engineering and Applied Sciences, University of Rochester（罗切斯特大学哈吉姆工程与应用科学学院）
In this paper, we set forth a new vision of reinforcement learning developed by us over the past few years, one that yields mathematically rigorous solutions to longstanding important questions that have remained unresolved: (i) how to design reliable, convergent, and robust reinforcement learning algorithms (ii) how to guarantee that reinforcement learning satisfies pre-specified "safety" guarantees, and remains in a stable region of the parameter space (iii) how to design "off-policy" temporal difference learning algorithms in a reliable and stable manner, and finally (iv) how to integrate t…
