Using privileged information during training can improve the sample efficiency and performance of machine learning systems. This paradigm has been applied to reinforcement learning (RL), primarily in the form of distillation or auxiliary tasks, and less commonly in the form of augmenting the inputs of agents. In this work, we investigate Privileged Information Dropout (\pid) for achieving the latter which can be applied equally to value-based and policy-based RL algorithms. Within a simple partially-observed environment, we demonstrate that \pid outperforms alternatives for leveraging privileged information, including distillation and auxiliary tasks, and can successfully utilise different types of privileged information. Finally, we analyse its effect on the learned representations.
Microsoft Research（微软研究院）；Georgia Institute of Technology（佐治亚理工学院）
Dropout has long been a staple of supervised learning, but is rarely used in reinforcement learning. We analyze why naive application of dropout is problematic for policy-gradient learning algorithms and introduce consistent dropout, a simple technique to address this instability. We demonstrate consistent dropout enables stable training with A2C and PPO in both continuous and discrete action environments across a wide range of dropout probabilities. Finally, we show that consistent dropout enables the online training of complex architectures such as GPT without needing to disable the model's …
Image-based Reinforcement Learning is known to suffer from poor sample efficiency and generalisation to unseen visuals such as distractors (task-independent aspects of the observation space). Visual domain randomisation encourages transfer by training over visual factors of variation that may be encountered in the target domain. This increases learning complexity, can negatively impact learning rate and performance, and requires knowledge of potential variations during deployment. In this paper, we introduce Attention-Privileged Reinforcement Learning (APRiL) which uses a self-supervised atten…
In this paper, we propose a new learning technique named message-dropout to improve the performance for multi-agent deep reinforcement learning under two application scenarios: 1) classical multi-agent reinforcement learning with direct message communication among agents and 2) centralized training with decentralized execution. In the first application scenario of multi-agent systems in which direct message communication among agents is allowed, the message-dropout technique drops out the received messages from other agents in a block-wise manner with a certain probability in the training phas…
PIGDreamer: Privileged Information Guided World Models for Safe Partially Observable Reinforcement Learning
School of Computer Science, University of Beihang, Beijing, China（北京航空航天大学计算机学院）；School of Computer Science, Chinese University of Hong Kong, Hongkong, China（香港中文大学计算机学院）；JD Explore Academy, Beijing, China（京东探索研究院）；North Automatic Control Institute, Taiyuan, China（太原北自动控制研究所）
NEC Corporation（日本电气股份有限公司）；National Institute of Advanced Industrial Science and Technology（日本产业技术综合研究所）；The University of Tokyo（东京大学）
Randomized ensembled double Q-learning (REDQ) (Chen et al., 2021b) has recently achieved state-of-the-art sample efficiency on continuous-action reinforcement learning benchmarks. This superior sample efficiency is made possible by using a large Q-function ensemble. However, REDQ is much less computationally efficient than non-ensemble counterparts such as Soft Actor-Critic (SAC) (Haarnoja et al., 2018a). To make REDQ more computationally efficient, we propose a method of improving computational efficiency called DroQ, which is a variant of REDQ that uses a small ensemble of dropout Q-function…
We consider the problem of detecting out-of-distribution (OOD) samples in deep reinforcement learning. In a value based reinforcement learning setting, we propose to use uncertainty estimation techniques directly on the agent's value estimating neural network to detect OOD samples. The focus of our work lies in analyzing the suitability of approximate Bayesian inference methods and related ensembling techniques that generate uncertainty estimates. Although prior work has shown that dropout-based variational inference techniques and bootstrap-based approaches can be used to model epistemic unce…
Traversing intersections is a challenging problem for autonomous vehicles, especially when the intersections do not have traffic control. Recently deep reinforcement learning has received massive attention due to its success in dealing with autonomous driving tasks. In this work, we address the problem of traversing unsignalized intersections using a novel curriculum for deep reinforcement learning. The proposed curriculum leads to: 1) A faster training process for the reinforcement learning agent, and 2) Better performance compared to an agent trained without curriculum. Our main contribution…
SoloParkour: Constrained Reinforcement Learning for Visual Locomotion from Privileged Experience
LAAS-CNRS（法国国家科学研究中心自动化与系统分析实验室）；Université de Toulouse（图卢兹大学）；CNRS（法国国家科学研究中心）；New York University（纽约大学）；Artificial and Natural Intelligence Toulouse Institute（图卢兹人工与自然智能研究所）
Unlike machines, humans learn through rapid, abstract model-building. The role of a teacher is not simply to hammer home right or wrong answers, but rather to provide intuitive comments, comparisons, and explanations to a pupil. This is what the Learning Under Privileged Information (LUPI) paradigm endeavors to model by utilizing extra knowledge only available during training. We propose a new LUPI algorithm specifically designed for Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). We propose to use a heteroscedastic dropout (i.e. dropout with a varying variance) and …
PR-OPD: Privileged Representation On-policy Self-Distillation for Agentic Reinforcement Learning
University of Florida（佛罗里达大学）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；Case Western Reserve University（凯斯西储大学）；Vanderbilt University（范德堡大学）；Weill Cornell Medicine（威尔康奈尔医学院）
Federal University of Espirito Santo, UFES（圣埃斯皮里图联邦大学）
High dropout rates in tertiary education expose a lack of efficiency that causes frustration of expectations and financial waste. Predicting students at risk is not enough to avoid student dropout. Usually, an appropriate aid action must be discovered and applied in the proper time for each student. To tackle this sequential decision-making problem, we propose a decision support method to the selection of aid actions for students using offline reinforcement learning to support decision-makers effectively avoid student dropout. Additionally, a discretization of student's state space applying tw…
Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)
Sch. of CS, Sch. of AIS, Sch. of AI, Shanghai Jiao Tong University（计算机科学学院、人工智能科学学院、人工智能学院，上海交通大学）；Institute of Trustworthy Embodied AI, Fudan University（可信具身人工智能研究院，复旦大学）；AgiBot
IDSIA（IDSIA研究所）；Università della Svizzera italiana（瑞士意大利语区大学）；TU Darmstadt（达姆施塔特工业大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Politecnico di Milano（米兰理工大学）
Reinforcement learning algorithms based on Q-learning are driving Deep Reinforcement Learning (DRL) research towards solving complex problems and achieving super-human performance on many of them. Nevertheless, Q-Learning is known to be positively biased since it learns by using the maximum over noisy estimates of expected values. Systematic overestimation of the action values coupled with the inherently high variance of DRL methods can lead to incrementally accumulate errors, causing learning algorithms to diverge. Ideally, we would like DRL agents to take into account their own uncertainty a…
Mila, University of Montreal（蒙特利尔大学Mila研究所）；Deepmind（深度思维公司）；University of California, Berkeley（加州大学伯克利分校）
In many applications, it is desirable to extract only the relevant information from complex input data, which involves making a decision about which input features are relevant. The information bottleneck method formalizes this as an information-theoretic optimization problem by maintaining an optimal tradeoff between compression (throwing away irrelevant input information), and predicting the target. In many problem settings, including the reinforcement learning problems we consider in this work, we might prefer to compress only part of the input. This is typically the case when we have a sta…
Northeastern University（东北大学）；Delft University of Technology（代尔夫特理工大学）
While reinforcement learning (RL) has made great advances in scalability, exploration and partial observability are still active research topics. In contrast, Bayesian RL (BRL) provides a principled answer to both state estimation and the exploration-exploitation trade-off, but struggles to scale. To tackle this challenge, BRL frameworks with various prior assumptions have been proposed, with varied success. This work presents a representation-agnostic formulation of BRL under partially observability, unifying the previous models under one theoretical umbrella. To demonstrate its practical sig…
Institute of Automation Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；School of Computer Science Carnegie Mellon University（卡内基梅隆大学计算机学院）
During the training of a reinforcement learning (RL) agent, the distribution of training data is non-stationary as the agent's behavior changes over time. Therefore, there is a risk that the agent is overspecialized to a particular distribution and its performance suffers in the larger picture. Ensemble RL can mitigate this issue by learning a robust policy. However, it suffers from heavy computational resource consumption due to the newly introduced value and policy functions. In this paper, to avoid the notorious resources consumption issue, we design a novel and simple ensemble deep RL fram…
Deep learning tools have gained tremendous attention in applied machine learning. However such tools for regression and classification do not capture model uncertainty. In comparison, Bayesian models offer a mathematically grounded framework to reason about model uncertainty, but usually come with a prohibitive computational cost. In this paper we develop a new theoretical framework casting dropout training in deep neural networks (NNs) as approximate Bayesian inference in deep Gaussian processes. A direct result of this theory gives us tools to model uncertainty with dropout NNs -- extracting…
Tencent Inc.（腾讯公司）；University of Manchester（曼彻斯特大学）
Recent success in Deep Reinforcement Learning (DRL) methods has shown that policy optimization with respect to an off-policy distribution via importance sampling is effective for sample reuse. In this paper, we show that the use of importance sampling could introduce high variance in the objective estimate. Specifically, we show in a principled way that the variance of importance sampling estimate grows quadratically with importance ratios and the large ratios could consequently jeopardize the effectiveness of surrogate objective optimization. We then propose a technique called sample dropout …
Reinforcement learning agents need exploratory behaviors to escape from local optima. These behaviors may include both immediate dithering perturbation and temporally consistent exploration. To achieve these, a stochastic policy model that is inherently consistent through a period of time is in desire, especially for tasks with either sparse rewards or long term information. In this work, we introduce a novel on-policy temporally consistent exploration strategy - Neural Adaptive Dropout Policy Exploration (NADPEx) - for deep reinforcement learning agents. Modeled as a global random variable fo…
Humans achieve efficient learning by relying on prior knowledge about the structure of naturally occurring tasks. There is considerable interest in designing reinforcement learning (RL) algorithms with similar properties. This includes proposals to learn the learning algorithm itself, an idea also known as meta learning. One formal interpretation of this idea is as a partially observable multi-task RL problem in which task information is hidden from the agent. Such unknown task problems can be reduced to Markov decision processes (MDPs) by augmenting an agent's observations with an estimate of…
In this research work, probabilistic decision-making approaches are studied, e.g. Bayesian and Boltzmann strategies, along with various deterministic exploration strategies, e.g. greedy, epsilon-Greedy and random approaches. In this research work, a comparative study has been done between probabilistic and deterministic decision-making approaches, the experiments are performed in OpenAI gym environment, solving Cart Pole problem. This research work discusses about the Bayesian approach to decision-making in deep reinforcement learning, and about dropout, how it can reduce the computational cos…
ETH Zürich（苏黎世联邦理工学院）；FZI Research Center for Information Technology（FZI信息技术研究中心）
The need for algorithms able to solve Reinforcement Learning (RL) problems with few trials has motivated the advent of model-based RL methods. The reported performance of model-based algorithms has dramatically increased within recent years. However, it is not clear how much of the recent progress is due to improved algorithms or due to improved models. While different modeling options are available to choose from when applying a model-based approach, the distinguishing traits and particular strengths of different models are not clear. The main contribution of this work lies precisely in asses…
Johns Hopkins University Applied Physics Laboratory（约翰斯·霍普金斯大学应用物理实验室）
One of the most fundamental design choices in neural networks is layer width: it affects the capacity of what a network can learn and determines the complexity of the solution. This latter property is often exploited when introducing information bottlenecks, forcing a network to learn compressed representations. However, such an architecture decision is typically immutable once training begins; switching to a more compressed architecture requires retraining. In this paper we present a new layer design, called Triangular Dropout, which does not have this limitation. After training, the layer ca…
In this paper, we investigate the problem of overfitting in deep reinforcement learning. Among the most common benchmarks in RL, it is customary to use the same environments for both training and testing. This practice offers relatively little insight into an agent's ability to generalize. We address this issue by using procedurally generated environments to construct distinct training and test sets. Most notably, we introduce a new environment called CoinRun, designed as a benchmark for generalization in RL. Using CoinRun, we find that agents overfit to surprisingly large training sets. We th…
