This paper studies the problem of learning a control policy without the need for interactions with the environment; instead, learning purely from an existing dataset. Prior work has demonstrated that offline learning algorithms (e.g., behavioural cloning and offline reinforcement learning) are more likely to discover a satisfactory policy when trained using high-quality expert data. However, many real-world/practical datasets can contain significant proportions of examples generated using low-skilled agents. Therefore, we propose a behaviour discriminator (BD) concept, a novel and simple data filtering approach based on semi-supervised learning, which can accurately discern expert data from a mixed-quality dataset. Our BD approach was used to pre-process the mixed-skill-level datasets from the Real Robot Challenge (RRC) III, an open competition requiring participants to solve several dexterous robotic manipulation tasks using offline learning methods; the new BD method allowed a standard behavioural cloning algorithm to outperform other more sophisticated offline learning algorithms. Moreover, we demonstrate that the new BD pre-processing method can be applied to a number of D4RL benchmark problems, improving the performance of multiple state-of-the-art offline reinforcement learning algorithms.
相關內容
With the fast improvement of machine learning, reinforcement learning (RL) has been used to automate human tasks in different areas. However, training such agents is difficult and restricted to expert users. Moreover, it is mostly limited to simulation environments due to the high cost and safety concerns of interactions in the real world. Demonstration Learning is a paradigm in which an agent learns to perform a task by imitating the behavior of an expert shown in demonstrations. It is a relatively recent area in machine learning, but it is gaining significant traction due to having tremendous potential for learning complex behaviors from demonstrations. Learning from demonstration accelerates the learning process by improving sample efficiency, while also reducing the effort of the programmer. Due to learning without interacting with the environment, demonstration learning would allow the automation of a wide range of real world applications such as robotics and healthcare. This paper provides a survey of demonstration learning, where we formally introduce the demonstration problem along with its main challenges and provide a comprehensive overview of the process of learning from demonstrations from the creation of the demonstration data set, to learning methods from demonstrations, and optimization by combining demonstration learning with different machine learning methods. We also review the existing benchmarks and identify their strengths and limitations. Additionally, we discuss the advantages and disadvantages of the paradigm as well as its main applications. Lastly, we discuss our perspective on open problems and research directions for this rapidly growing field.
In modern industrial collaborative robotic applications, it is desirable to create robot programs automatically, intuitively, and time-efficiently. Moreover, robots need to be controlled by reactive policies to face the unpredictability of the environment they operate in. In this paper we propose a framework that combines a method that learns Behavior Trees (BTs) from demonstration with a method that evolves them with Genetic Programming (GP) for collaborative robotic applications. The main contribution of this paper is to show that by combining the two learning methods we obtain a method that allows non-expert users to semi-automatically, time-efficiently, and interactively generate BTs. We validate the framework with a series of manipulation experiments. The BT is fully learnt in simulation and then transferred to a real collaborative robot.
Missing data is a commonly occurring problem in practice. Many imputation methods have been developed to fill in the missing entries. However, not all of them can scale to high-dimensional data, especially the multiple imputation techniques. Meanwhile, the data nowadays tends toward high-dimensional. Therefore, in this work, we propose Principal Component Analysis Imputation (PCAI), a simple but versatile framework based on Principal Component Analysis (PCA) to speed up the imputation process and alleviate memory issues of many available imputation techniques, without sacrificing the imputation quality in term of MSE. In addition, the frameworks can be used even when some or all of the missing features are categorical, or when the number of missing features is large. Next, we introduce PCA Imputation - Classification (PIC), an application of PCAI for classification problems with some adjustments. We validate our approach by experiments on various scenarios, which shows that PCAI and PIC can work with various imputation algorithms, including the state-of-the-art ones and improve the imputation speed significantly, while achieving competitive mean square error/classification accuracy compared to direct imputation (i.e., impute directly on the missing data).
Offline reinforcement learning (RL) aims to infer sequential decision policies using only offline datasets. This is a particularly difficult setup, especially when learning to achieve multiple different goals or outcomes under a given scenario with only sparse rewards. For offline learning of goal-conditioned policies via supervised learning, previous work has shown that an advantage weighted log-likelihood loss guarantees monotonic policy improvement. In this work we argue that, despite its benefits, this approach is still insufficient to fully address the distribution shift and multi-modality problems. The latter is particularly severe in long-horizon tasks where finding a unique and optimal policy that goes from a state to the desired goal is challenging as there may be multiple and potentially conflicting solutions. To tackle these challenges, we propose a complementary advantage-based weighting scheme that introduces an additional source of inductive bias: given a value-based partitioning of the state space, the contribution of actions expected to lead to target regions that are easier to reach, compared to the final goal, is further increased. Empirically, we demonstrate that the proposed approach, Dual-Advantage Weighted Offline Goal-conditioned RL (DAWOG), outperforms several competing offline algorithms in commonly used benchmarks. Analytically, we offer a guarantee that the learnt policy is never worse than the underlying behaviour policy.
Prescriptive Process Monitoring is a prominent problem in Process Mining, which consists in identifying a set of actions to be recommended with the goal of optimising a target measure of interest or Key Performance Indicator (KPI). One challenge that makes this problem difficult is the need to provide Prescriptive Process Monitoring techniques only based on temporally annotated (process) execution data, stored in, so-called execution logs, due to the lack of well crafted and human validated explicit models. In this paper we aim at proposing an AI based approach that learns, by means of Reinforcement Learning (RL), an optimal policy (almost) only from the observation of past executions and recommends the best activities to carry on for optimizing a KPI of interest. This is achieved first by learning a Markov Decision Process for the specific KPIs from data, and then by using RL training to learn the optimal policy. The approach is validated on real and synthetic datasets and compared with off-policy Deep RL approaches. The ability of our approach to compare with, and often overcome, Deep RL approaches provides a contribution towards the exploitation of white box RL techniques in scenarios where only temporal execution data are available.
Sequential decision making in the real world often requires finding a good balance of conflicting objectives. In general, there exist a plethora of Pareto-optimal policies that embody different patterns of compromises between objectives, and it is technically challenging to obtain them exhaustively using deep neural networks. In this work, we propose a novel multi-objective reinforcement learning (MORL) algorithm that trains a single neural network via policy gradient to approximately obtain the entire Pareto set in a single run of training, without relying on linear scalarization of objectives. The proposed method works in both continuous and discrete action spaces with no design change of the policy network. Numerical experiments in benchmark environments demonstrate the practicality and efficacy of our approach in comparison to standard MORL baselines.
Behaviors of the synthetic characters in current military simulations are limited since they are generally generated by rule-based and reactive computational models with minimal intelligence. Such computational models cannot adapt to reflect the experience of the characters, resulting in brittle intelligence for even the most effective behavior models devised via costly and labor-intensive processes. Observation-based behavior model adaptation that leverages machine learning and the experience of synthetic entities in combination with appropriate prior knowledge can address the issues in the existing computational behavior models to create a better training experience in military training simulations. In this paper, we introduce a framework that aims to create autonomous synthetic characters that can perform coherent sequences of believable behavior while being aware of human trainees and their needs within a training simulation. This framework brings together three mutually complementary components. The first component is a Unity-based simulation environment - Rapid Integration and Development Environment (RIDE) - supporting One World Terrain (OWT) models and capable of running and supporting machine learning experiments. The second is Shiva, a novel multi-agent reinforcement and imitation learning framework that can interface with a variety of simulation environments, and that can additionally utilize a variety of learning algorithms. The final component is the Sigma Cognitive Architecture that will augment the behavior models with symbolic and probabilistic reasoning capabilities. We have successfully created proof-of-concept behavior models leveraging this framework on realistic terrain as an essential step towards bringing machine learning into military simulations.
Recently, neural networks have been widely used in e-commerce recommender systems, owing to the rapid development of deep learning. We formalize the recommender system as a sequential recommendation problem, intending to predict the next items that the user might be interacted with. Recent works usually give an overall embedding from a user's behavior sequence. However, a unified user embedding cannot reflect the user's multiple interests during a period. In this paper, we propose a novel controllable multi-interest framework for the sequential recommendation, called ComiRec. Our multi-interest module captures multiple interests from user behavior sequences, which can be exploited for retrieving candidate items from the large-scale item pool. These items are then fed into an aggregation module to obtain the overall recommendation. The aggregation module leverages a controllable factor to balance the recommendation accuracy and diversity. We conduct experiments for the sequential recommendation on two real-world datasets, Amazon and Taobao. Experimental results demonstrate that our framework achieves significant improvements over state-of-the-art models. Our framework has also been successfully deployed on the offline Alibaba distributed cloud platform.
Recommender systems play a crucial role in mitigating the problem of information overload by suggesting users' personalized items or services. The vast majority of traditional recommender systems consider the recommendation procedure as a static process and make recommendations following a fixed strategy. In this paper, we propose a novel recommender system with the capability of continuously improving its strategies during the interactions with users. We model the sequential interactions between users and a recommender system as a Markov Decision Process (MDP) and leverage Reinforcement Learning (RL) to automatically learn the optimal strategies via recommending trial-and-error items and receiving reinforcements of these items from users' feedbacks. In particular, we introduce an online user-agent interacting environment simulator, which can pre-train and evaluate model parameters offline before applying the model online. Moreover, we validate the importance of list-wise recommendations during the interactions between users and agent, and develop a novel approach to incorporate them into the proposed framework LIRD for list-wide recommendations. The experimental results based on a real-world e-commerce dataset demonstrate the effectiveness of the proposed framework.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191