Towards Applicable Reinforcement Learning: Improving the Generalization and Sample Efficiency with Policy Ensemble

It is challenging for reinforcement learning (RL) algorithms to succeed in real-world applications like financial trading and logistic system due to the noisy observation and environment shifting between training and evaluation. Thus, it requires both high sample efficiency and generalization for resolving real-world tasks. However, directly applying typical RL algorithms can lead to poor performance in such scenarios. Considering the great performance of ensemble methods on both accuracy and generalization in supervised learning (SL), we design a robust and applicable method named Ensemble Proximal Policy Optimization (EPPO), which learns ensemble policies in an end-to-end manner. Notably, EPPO combines each policy and the policy ensemble organically and optimizes both simultaneously. In addition, EPPO adopts a diversity enhancement regularization over the policy space which helps to generalize to unseen states and promotes exploration. We theoretically prove EPPO increases exploration efficacy, and through comprehensive experimental evaluations on various tasks, we demonstrate that EPPO achieves higher efficiency and is robust for real-world applications compared with vanilla policy optimization algorithms and other ensemble methods. Code and supplemental materials are available at https://seqml.github.io/eppo.

Curriculum Offline Imitation Learning

Offline reinforcement learning (RL) tasks require the agent to learn from a pre-collected dataset with no further interactions with the environment. Despite the potential to surpass the behavioral policies, RL-based methods are generally impractical due to the training instability and bootstrapping the extrapolation errors, which always require careful hyperparameter tuning via online evaluation. In contrast, offline imitation learning (IL) has no such issues since it learns the policy directly without estimating the value function by bootstrapping. However, IL is usually limited in the capability of the behavioral policy and tends to learn a mediocre behavior from the dataset collected by the mixture of policies. In this paper, we aim to take advantage of IL but mitigate such a drawback. Observing that behavior cloning is able to imitate neighboring policies with less data, we propose \textit{Curriculum Offline Imitation Learning (COIL)}, which utilizes an experience picking strategy for imitating from adaptive neighboring policies with a higher return, and improves the current policy along curriculum stages. On continuous control benchmarks, we compare COIL against both imitation-based and RL-based methods, showing that it not only avoids just learning a mediocre behavior on mixed datasets but is also even competitive with state-of-the-art offline RL methods.

SSFL: Tackling Label Deficiency in Federated Learning via Personalized Self-Supervision

Federated Learning (FL) is transforming the ML training ecosystem from a centralized over-the-cloud setting to distributed training over edge devices in order to strengthen data privacy. An essential but rarely studied challenge in FL is label deficiency at the edge. This problem is even more pronounced in FL compared to centralized training due to the fact that FL users are often reluctant to label their private data. Furthermore, due to the heterogeneous nature of the data at edge devices, it is crucial to develop personalized models. In this paper we propose self-supervised federated learning (SSFL), a unified self-supervised and personalized federated learning framework, and a series of algorithms under this framework which work towards addressing these challenges. First, under the SSFL framework, we demonstrate that the standard FedAvg algorithm is compatible with recent breakthroughs in centralized self-supervised learning such as SimSiam networks. Moreover, to deal with data heterogeneity at the edge devices in this framework, we have innovated a series of algorithms that broaden existing supervised personalization algorithms into the setting of self-supervised learning. We further propose a novel personalized federated self-supervised learning algorithm, Per-SSFL, which balances personalization and consensus by carefully regulating the distance between the local and global representations of data. To provide a comprehensive comparative analysis of all proposed algorithms, we also develop a distributed training system and related evaluation protocol for SSFL. Our findings show that the gap of evaluation accuracy between supervised learning and unsupervised learning in FL is both small and reasonable. The performance comparison indicates the representation regularization-based personalization method is able to outperform other variants.

SimPLE: Similar Pseudo Label Exploitation for Semi-Supervised Classification

A common classification task situation is where one has a large amount of data available for training, but only a small portion is annotated with class labels. The goal of semi-supervised training, in this context, is to improve classification accuracy by leverage information not only from labeled data but also from a large amount of unlabeled data. Recent works have developed significant improvements by exploring the consistency constrain between differently augmented labeled and unlabeled data. Following this path, we propose a novel unsupervised objective that focuses on the less studied relationship between the high confidence unlabeled data that are similar to each other. The new proposed Pair Loss minimizes the statistical distance between high confidence pseudo labels with similarity above a certain threshold. Combining the Pair Loss with the techniques developed by the MixMatch family, our proposed SimPLE algorithm shows significant performance gains over previous algorithms on CIFAR-100 and Mini-ImageNet, and is on par with the state-of-the-art methods on CIFAR-10 and SVHN. Furthermore, SimPLE also outperforms the state-of-the-art methods in the transfer learning setting, where models are initialized by the weights pre-trained on ImageNet or DomainNet-Real. The code is available at github.com/zijian-hu/SimPLE.

To Follow or not to Follow: Selective Imitation Learning from Observations

Learning from demonstrations is a useful way to transfer a skill from one agent to another. While most imitation learning methods aim to mimic an expert skill by following the demonstration step-by-step, imitating every step in the demonstration often becomes infeasible when the learner and its environment are different from the demonstration. In this paper, we propose a method that can imitate a demonstration composed solely of observations, which may not be reproducible with the current agent. Our method, dubbed selective imitation learning from observations (SILO), selects reachable states in the demonstration and learns how to reach the selected states. Our experiments on both simulated and real robot environments show that our method reliably performs a new task by following a demonstration. Videos and code are available at https://clvrai.com/silo .

IKEA Furniture Assembly Environment for Long-Horizon Complex Manipulation Tasks

The IKEA Furniture Assembly Environment is one of the first benchmarks for testing and accelerating the automation of complex manipulation tasks. The environment is designed to advance reinforcement learning from simple toy tasks to complex tasks requiring both long-term planning and sophisticated low-level control. Our environment supports over 80 different furniture models, Sawyer and Baxter robot simulation, and domain randomization. The IKEA Furniture Assembly Environment is a testbed for methods aiming to solve complex manipulation tasks. The environment is publicly available at https://clvrai.com/furniture

Deep Landscape Forecasting for Real-time Bidding Advertising

The emergence of real-time auction in online advertising has drawn huge attention of modeling the market competition, i.e., bid landscape forecasting. The problem is formulated as to forecast the probability distribution of market price for each ad auction. With the consideration of the censorship issue which is caused by the second-price auction mechanism, many researchers have devoted their efforts on bid landscape forecasting by incorporating survival analysis from medical research field. However, most existing solutions mainly focus on either counting-based statistics of the segmented sample clusters, or learning a parameterized model based on some heuristic assumptions of distribution forms. Moreover, they neither consider the sequential patterns of the feature over the price space. In order to capture more sophisticated yet flexible patterns at fine-grained level of the data, we propose a Deep Landscape Forecasting (DLF) model which combines deep learning for probability distribution forecasting and survival analysis for censorship handling. Specifically, we utilize a recurrent neural network to flexibly model the conditional winning probability w.r.t. each bid price. Then we conduct the bid landscape forecasting through probability chain rule with strict mathematical derivations. And, in an end-to-end manner, we optimize the model by minimizing two negative likelihood losses with comprehensive motivations. Without any specific assumption for the distribution form of bid landscape, our model shows great advantages over previous works on fitting various sophisticated market price distributions. In the experiments over two large-scale real-world datasets, our model significantly outperforms the state-of-the-art solutions under various metrics.

Deep Recurrent Survival Analysis

Survival analysis is a hotspot in statistical research for modeling time-to-event information with data censorship handling, which has been widely used in many applications such as clinical research, information system and other fields with survivorship bias. Many works have been proposed for survival analysis ranging from traditional statistic methods to machine learning models. However, the existing methodologies either utilize counting-based statistics on the segmented data, or have a pre-assumption on the event probability distribution w.r.t. time. Moreover, few works consider sequential patterns within the feature space. In this paper, we propose a Deep Recurrent Survival Analysis model which combines deep learning for conditional probability prediction at fine-grained level of the data, and survival analysis for tackling the censorship. By capturing the time dependency through modeling the conditional probability of the event for each sample, our method predicts the likelihood of the true event occurrence and estimates the survival rate over time, i.e., the probability of the non-occurrence of the event, for the censored data. Meanwhile, without assuming any specific form of the event probability distribution, our model shows great advantages over the previous works on fitting various sophisticated data distributions. In the experiments on the three real-world tasks from different fields, our model significantly outperforms the state-of-the-art solutions under various metrics.

Geometric Semantic Genetic Programming Algorithm and Slump Prediction

Research on the performance of recycled concrete as building material in the current world is an important subject. Given the complex composition of recycled concrete, conventional methods for forecasting slump scarcely obtain satisfactory results. Based on theory of nonlinear prediction method, we propose a recycled concrete slump prediction model based on geometric semantic genetic programming (GSGP) and combined it with recycled concrete features. Tests show that the model can accurately predict the recycled concrete slump by using the established prediction model to calculate the recycled concrete slump with different mixing ratios in practical projects and by comparing the predicted values with the experimental values. By comparing the model with several other nonlinear prediction models, we can conclude that GSGP has higher accuracy and reliability than conventional methods.

Slope Stability Analysis with Geometric Semantic Genetic Programming

Genetic programming has been widely used in the engineering field. Compared with the conventional genetic programming and artificial neural network, geometric semantic genetic programming (GSGP) is superior in astringency and computing efficiency. In this paper, GSGP is adopted for the classification and regression analysis of a sample dataset. Furthermore, a model for slope stability analysis is established on the basis of geometric semantics. According to the results of the study based on GSGP, the method can analyze slope stability objectively and is highly precise in predicting slope stability and safety factors. Hence, the predicted results can be used as a reference for slope safety design.