Standard RL algorithms assume fixed environment dynamics and require a significant amount of interaction to adapt to new environments. We introduce Policy-Dynamics Value Functions (PD-VF), a novel approach for rapidly adapting to dynamics different from those previously seen in training. PD-VF explicitly estimates the cumulative reward in a space of policies and environments. An ensemble of conventional RL policies is used to gather experience on training environments, from which embeddings of both policies and environments can be learned. Then, a value function conditioned on both embeddings is trained. At test time, a few actions are sufficient to infer the environment embedding, enabling a policy to be selected by maximizing the learned value function (which requires no additional environment interaction). We show that our method can rapidly adapt to new dynamics on a set of MuJoCo domains. Code available at https://github.com/rraileanu/policy-dynamics-value-functions.
College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）；Northwestern Polytechnical University（西北工业大学）
Deep Reinforcement Learning (DRL) has been a promising solution to many complex decision-making problems. Nevertheless, the notorious weakness in generalization among environments prevent widespread application of DRL agents in real-world scenarios. Although advances have been made recently, most prior works assume sufficient online interaction on training environments, which can be costly in practical cases. To this end, we focus on an offline-training-online-adaptation setting, in which the agent first learns from offline experiences collected in environments with different dynamics and then…
We introduce a new algorithm for multi-objective reinforcement learning (MORL) with linear preferences, with the goal of enabling few-shot adaptation to new tasks. In MORL, the aim is to learn policies over multiple competing objectives whose relative importance (preferences) is unknown to the agent. While this alleviates dependence on scalar reward design, the expected return of a policy can change significantly with varying preferences, making it challenging to learn a single model to produce optimal policies under different preference conditions. We propose a generalized version of the Bell…
University of Cambridge（剑桥大学）；Google（谷歌）；Google Research（谷歌研究院）
One of the most challenging aspects of real-world reinforcement learning (RL) is the multitude of unpredictable and ever-changing distractions that could divert an agent from what was tasked to do in its training environment. While an agent could learn from reward signals to ignore them, the complexity of the real-world can make rewards hard to acquire, or, at best, extremely sparse. A recent class of self-supervised methods have shown promise that reward-free adaptation under challenging distractions is possible. However, previous work focused on a short one-episode adaptation setting. In thi…
Transferable Reinforcement Learning via Probabilistic Latent Embeddings and Dynamic Policy Adaptation for Sim-to-Real Deployment
Lyles School of Civil and Construction Engineering, Purdue University, West Lafayette, USA（普渡大学土木与建设工程学院）；Elmore Family School of Electrical and Computer Engineering, Purdue University, West Lafayette, USA（普渡大学埃尔莫尔家庭电气与计算机工程学院）
The ability to exploit prior experience to solve novel problems rapidly is a hallmark of biological learning systems and of great practical importance for artificial ones. In the meta reinforcement learning literature much recent work has focused on the problem of optimizing the learning process itself. In this paper we study a complementary approach which is conceptually simple, general, modular and built on top of recent improvements in off-policy learning. The framework is inspired by ideas from the probabilistic inference literature and combines robust off-policy learning with a behavior p…
This paper introduces Fast Linearized Adaptive Policy (FLAP), a new meta-reinforcement learning (meta-RL) method that is able to extrapolate well to out-of-distribution tasks without the need to reuse data from training, and adapt almost instantaneously with the need of only a few samples during testing. FLAP builds upon the idea of learning a shared linear representation of the policy so that when adapting to a new task, it suffices to predict a set of linear weights. A separate adapter network is trained simultaneously with the policy such that during adaptation, we can directly use the adap…
The Ohio State University（俄亥俄州立大学）；The Ohio State University Wexner Medical Center（俄亥俄州立大学韦克斯纳医学中心）
Despite intense efforts in basic and clinical research, an individualized ventilation strategy for critically ill patients remains a major challenge. Recently, dynamic treatment regime (DTR) with reinforcement learning (RL) on electronic health records (EHR) has attracted interest from both the healthcare industry and machine learning research community. However, most learned DTR policies might be biased due to the existence of confounders. Although some treatment actions non-survivors received may be helpful, if confounders cause the mortality, the training of RL models guided by long-term ou…
There has been a recent focus in reinforcement learning on addressing continuous state and action problems by optimizing parameterized policies. PI2 is a recent example of this approach. It combines a derivation from first principles of stochastic optimal control with tools from statistical estimation theory. In this paper, we consider PI2 as a member of the wider family of methods which share the concept of probability-weighted averaging to iteratively update parameters to optimize a cost function. We compare PI2 to other members of the same family - Cross-Entropy Methods and CMAES - at the c…
Preferred Networks, Inc.（优选网络公司）；University of Toronto（多伦多大学）
In this paper we target the problem of transferring policies across multiple environments with different dynamics parameters and motor noise variations, by introducing a framework that decouples the processes of policy learning and system identification. Efficiently transferring learned policies to an unknown environment with changes in dynamics configurations in the presence of motor noise is very important for operating robots in the real world, and our work is a novel attempt in that direction. We introduce MANGA: Method Agnostic Neural-policy Generalization and Adaptation, that trains dyna…
Policy-Driven World Model Adaptation for Robust Offline Model-based Reinforcement Learning
The University of Hong Kong, Hong Kong SAR（香港大学）；INFIFORCE Intelligent Technology Co., Ltd., Hangzhou, China（INFIFORCE智能技术有限公司）；Tsinghua University, Beijing, China（清华大学）；Carnegie Mellon University, Pittsburgh, PA 15213, USA（卡内基梅隆大学）
Hierarchical reinforcement learning is a promising approach to tackle long-horizon decision-making problems with sparse rewards. Unfortunately, most methods still decouple the lower-level skill acquisition process and the training of a higher level that controls the skills in a new task. Leaving the skills fixed can lead to significant sub-optimality in the transfer setting. In this work, we propose a novel algorithm to discover a set of skills, and continuously adapt them along with the higher level even when training on a new task. Our main contributions are two-fold. First, we derive a new …
Shanghai Jiao Tong University（上海交通大学）；D. E. Shaw & Co（D.E.肖公司）；Carnegie Mellon University（卡内基梅隆大学）
Model-based reinforcement learning methods learn a dynamics model with real data sampled from the environment and leverage it to generate simulated data to derive an agent. However, due to the potential distribution mismatch between simulated data and real data, this could lead to degraded performance. Despite much effort being devoted to reducing this distribution mismatch, existing methods fail to solve it explicitly. In this paper, we investigate how to bridge the gap between real and simulated data due to inaccurate model estimation for better policy optimization. To begin with, we first d…
Coordinated Sciences Laboratory, University of Illinois, Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校协调科学实验室）
Efficient and robust policy transfer remains a key challenge for reinforcement learning to become viable for real-wold robotics. Policy transfer through warm initialization, imitation, or interacting over a large set of agents with randomized instances, have been commonly applied to solve a variety of Reinforcement Learning tasks. However, this seems far from how skill transfer happens in the biological world: Humans and animals are able to quickly adapt the learned behaviors between similar tasks and learn new skills when presented with new situations. Here we seek to answer the question: Wil…
QPPG: Quantum-Preconditioned Policy Gradient for Link Adaptation in Rayleigh Fading Channels
African Institute for Mathematical Sciences（非洲数学科学研究所）；Stanford University（斯坦福大学）；Olabisi Onabanjo University（奥拉比·奥纳班乔大学）；University of Glasgow（格拉斯哥大学）
Robotics Innovation Center, DFKI GmbH（德国人工智能研究中心有限公司机器人创新中心）
Contextual policy search (CPS) is a class of multi-task reinforcement learning algorithms that is particularly useful for robotic applications. A recent state-of-the-art method is Contextual Covariance Matrix Adaptation Evolution Strategies (C-CMA-ES). It is based on the standard black-box optimization algorithm CMA-ES. There are two useful extensions of CMA-ES that we will transfer to C-CMA-ES and evaluate empirically: ACM-ES, which uses a comparison-based surrogate model, and aCMA-ES, which uses an active update of the covariance matrix. We will show that improvements with these methods can …
Proximal Policy Optimization (PPO) is a highly popular model-free reinforcement learning (RL) approach. However, we observe that in a continuous action space, PPO can prematurely shrink the exploration variance, which leads to slow progress and may make the algorithm prone to getting stuck in local optima. Drawing inspiration from CMA-ES, a black-box evolutionary optimization method designed for robustness in similar situations, we propose PPO-CMA, a proximal policy optimization approach that adaptively expands the exploration variance to speed up progress. With only minor changes to PPO, our …
University of Michigan（密歇根大学）；Ford Research and Advanced Engineering（福特研究与高级工程中心）
Meta Reinforcement Learning (Meta-RL) has seen substantial advancements recently. In particular, off-policy methods were developed to improve the data efficiency of Meta-RL techniques. \textit{Probabilistic embeddings for actor-critic RL} (PEARL) is a leading approach for multi-MDP adaptation problems. A major drawback of many existing Meta-RL methods, including PEARL, is that they do not explicitly consider the safety of the prior policy when it is exposed to a new task for the first time. Safety is essential for many real-world applications, including field robots and Autonomous Vehicles (AV…
We propose a method to automatically generate a domain- and task-adaptive maskings of the given text for self-supervised pre-training, such that we can effectively adapt the language model to a particular target task (e.g. question answering). Specifically, we present a novel reinforcement learning-based framework which learns the masking policy, such that using the generated masks for further pre-training of the target language model helps improve task performance on unseen texts. We use off-policy actor-critic with entropy regularization and experience replay for reinforcement learning, and …
UC Berkeley（加州大学伯克利分校）；KIT（卡尔斯鲁厄理工学院）；Karlsruhe Inst. of Technology (KIT)（卡尔斯鲁厄理工学院）
Credit assignment in Meta-reinforcement learning (Meta-RL) is still poorly understood. Existing methods either neglect credit assignment to pre-adaptation behavior or implement it naively. This leads to poor sample-efficiency during meta-training as well as ineffective task identification strategies. This paper provides a theoretical analysis of credit assignment in gradient-based Meta-RL. Building on the gained insights we develop a novel meta-learning algorithm that overcomes both the issue of poor credit assignment and previous difficulties in estimating meta-policy gradients. By controllin…
Transferring reinforcement learning policies trained in physics simulation to the real hardware remains a challenge, known as the "sim-to-real" gap. Domain randomization is a simple yet effective technique to address dynamics discrepancies across source and target domains, but its success generally depends on heuristics and trial-and-error. In this work we investigate the impact of randomized parameter selection on policy transferability across different types of domain discrepancies. Contrary to common practice in which kinematic parameters are carefully measured while dynamic parameters are …
Hyper-Decision Transformer for Efficient Online Policy Adaptation
Carnegie Mellon University（卡内基梅隆大学）；University of Montreal（蒙特利尔大学）；Mila（米拉人工智能研究所）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；UMass Amherst（马萨诸塞大学阿默斯特分校）
AdaptNet: Policy Adaptation for Physics-Based Character Control
Clemson University（克莱姆森大学）；Roblox（Roblox公司）；McGill University（麦吉尔大学）；École de Technologie Supérieure（蒙特利尔高等技术学院）；University of California, Davis（加州大学戴维斯分校）；University of Waterloo（滑铁卢大学）；University of California, Riverside（加州大学河滨分校）
Carnegie Mellon University（卡内基梅隆大学）；Ecole Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）；King Abdulaziz City for Science and Technology（阿卜杜勒阿齐兹国王科技城）
Partially Detected Intelligent Traffic Signal Control (PD-ITSC) systems that can optimize traffic signals based on limited detected information could be a cost-efficient solution for mitigating traffic congestion in the future. In this paper, we focus on a particular problem in PD-ITSC - adaptation to changing environments. To this end, we investigate different reinforcement learning algorithms, including Q-learning, Proximal Policy Optimization (PPO), Advantage Actor-Critic (A2C), and Actor-Critic with Kronecker-Factored Trust Region (ACKTR). Our findings suggest that RL algorithms can find o…
Aalto University（阿尔托大学）；KTH Royal Institute of Technology（瑞典皇家理工学院）；KU Leuven（鲁汶大学）
Few-shot adaptation is a challenging problem in the context of simulation-to-real transfer in robotics, requiring safe and informative data collection. In physical systems, additional challenge may be posed by domain noise, which is present in virtually all real-world applications. In this paper, we propose to perform few-shot adaptation of dynamics models in noisy conditions using an uncertainty-aware Kalman filter-based neural network architecture. We show that the proposed method, which explicitly addresses domain noise, improves few-shot adaptation error over a blackbox adaptation LSTM bas…
University of California Berkeley（加州大学伯克利分校）；Carnegie Mellon University（卡内基梅隆大学）
Recent advances in legged locomotion have enabled quadrupeds to walk on challenging terrains. However, bipedal robots are inherently more unstable and hence it's harder to design walking controllers for them. In this work, we leverage recent advances in rapid adaptation for locomotion control, and extend them to work on bipedal robots. Similar to existing works, we start with a base policy which produces actions while taking as input an estimated extrinsics vector from an adaptation module. This extrinsics vector contains information about the environment and enables the walking controller to …
IRI, CSIC-UPC（加泰罗尼亚理工大学西班牙国家研究委员会机器人研究所）；UC Berkeley（加州大学伯克利分校）；NYU（纽约大学）；UC San Diego（加州大学圣迭戈分校）；Technical University of Denmark（丹麦技术大学）
In most real world scenarios, a policy trained by reinforcement learning in one environment needs to be deployed in another, potentially quite different environment. However, generalization across different environments is known to be hard. A natural solution would be to keep training after deployment in the new environment, but this cannot be done if the new environment offers no reward signal. Our work explores the use of self-supervision to allow the policy to continue training after deployment without using any rewards. While previous methods explicitly anticipate changes in the new enviro…
Ludwig-Maximilians University（路德维希-马克西米利安大学）；Technical University of Munich（慕尼黑工业大学）；Siemens Technology（西门子技术研究院）
Safe Policy Improvement (SPI) is an important technique for offline reinforcement learning in safety critical applications as it improves the behavior policy with a high probability. We classify various SPI approaches from the literature into two groups, based on how they utilize the uncertainty of state-action pairs. Focusing on the Soft-SPIBB (Safe Policy Improvement with Soft Baseline Bootstrapping) algorithms, we show that their claim of being provably safe does not hold. Based on this finding, we develop adaptations, the Adv-Soft-SPIBB algorithms, and show that they are provably safe. A h…
Reinforcement learning (RL) algorithms have been successfully used to develop control policies for dynamical systems. For many such systems, these policies are trained in a simulated environment. Due to discrepancies between the simulated model and the true system dynamics, RL trained policies often fail to generalize and adapt appropriately when deployed in the real-world environment. Current research in bridging this sim-to-real gap has largely focused on improvements in simulation design and on the development of improved and specialized RL algorithms for robust control policy generation. I…
Institute of Cyber-Systems and Control, College of Control Science and Engineering, Zhejiang University（浙江大学控制科学与工程学院 cyber-system 与控制研究所）；Huzhou Institute, Zhejiang University（浙江大学湖州研究院）
Parameter adaptation, that is the capability to automatically adjust an algorithm's hyperparameters depending on the problem being faced, is one of the main trends in evolutionary computation applied to numerical optimization. While several handcrafted adaptation policies have been proposed over the years to address this problem, only few attempts have been done so far at applying machine learning to learn such policies. Here, we introduce a general-purpose framework for performing parameter adaptation in continuous-domain metaheuristics based on state-of-the-art reinforcement learning algorit…
Uppsala University（乌普萨拉大学）；KTH Royal Institute of Technology（KTH皇家理工学院）
In socially assistive robotics, an important research area is the development of adaptation techniques and their effect on human-robot interaction. We present a meta-learning based policy gradient method for addressing the problem of adaptation in human-robot interaction and also investigate its role as a mechanism for trust modelling. By building an escape room scenario in mixed reality with a robot, we test our hypothesis that bi-directional trust can be influenced by different adaptation algorithms. We found that our proposed model increased the perceived trustworthiness of the robot and in…
MoVie: Visual Model-Based Policy Adaptation for View Generalization
Shanghai Qi Zhi Institute（上海期智研究院）；University of Electronic Science and Technology of China（电子科技大学）；Shanghai Jiao Tong University（上海交通大学）；Tsinghua University（清华大学）；Shanghai AI Lab（上海人工智能实验室）
In this work, we propose a framework for allowing autonomous robots deployed for extended periods of time in public spaces to adapt their own behaviour online from user interactions. The robot behaviour planning is embedded in a Reinforcement Learning (RL) framework, where the objective is maximising the level of overall user engagement during the interactions. We use the Upper-Confidence-Bound Value-Iteration (UCBVI) algorithm, which gives a helpful way of managing the exploration-exploitation trade-off for real-time interactions. An engagement model trained end-to-end generates the reward fu…
