Rui Chen

Weiye Zhao, Rui Chen, Yifan Sun et al.

Reinforcement Learning (RL) algorithms have shown tremendous success in simulation environments, but their application to real-world problems faces significant challenges, with safety being a major concern. In particular, enforcing state-wise constraints is essential for many challenging tasks such as autonomous driving and robot manipulation. However, existing safe RL algorithms under the framework of Constrained Markov Decision Process (CMDP) do not consider state-wise constraints. To address this gap, we propose State-wise Constrained Policy Optimization (SCPO), the first general-purpose policy search algorithm for state-wise constrained reinforcement learning. SCPO provides guarantees for state-wise constraint satisfaction in expectation. In particular, we introduce the framework of Maximum Markov Decision Process, and prove that the worst-case safety violation is bounded under SCPO. We demonstrate the effectiveness of our approach on training neural network policies for extensive robot locomotion tasks, where the agent must satisfy a variety of state-wise safety constraints. Our results show that SCPO significantly outperforms existing methods and can handle state-wise constraints in high-dimensional robotics tasks.

Ruixiang Tang, Jiayi Yuan, Yiming Li et al.

In the field of natural language processing, the prevalent approach involves fine-tuning pretrained language models (PLMs) using local samples. Recent research has exposed the susceptibility of PLMs to backdoor attacks, wherein the adversaries can embed malicious prediction behaviors by manipulating a few training samples. In this study, our objective is to develop a backdoor-resistant tuning procedure that yields a backdoor-free model, no matter whether the fine-tuning dataset contains poisoned samples. To this end, we propose and integrate a honeypot module into the original PLM, specifically designed to absorb backdoor information exclusively. Our design is motivated by the observation that lower-layer representations in PLMs carry sufficient backdoor features while carrying minimal information about the original tasks. Consequently, we can impose penalties on the information acquired by the honeypot module to inhibit backdoor creation during the fine-tuning process of the stem network. Comprehensive experiments conducted on benchmark datasets substantiate the effectiveness and robustness of our defensive strategy. Notably, these results indicate a substantial reduction in the attack success rate ranging from 10\% to 40\% when compared to prior state-of-the-art methods.

Alvin Shek, Bo Ying Su, Rui Chen et al.

For robots to be effectively deployed in novel environments and tasks, they must be able to understand the feedback expressed by humans during intervention. This can either correct undesirable behavior or indicate additional preferences. Existing methods either require repeated episodes of interactions or assume prior known reward features, which is data-inefficient and can hardly transfer to new tasks. We relax these assumptions by describing human tasks in terms of object-centric sub-tasks and interpreting physical interventions in relation to specific objects. Our method, Object Preference Adaptation (OPA), is composed of two key stages: 1) pre-training a base policy to produce a wide variety of behaviors, and 2) online-updating according to human feedback. The key to our fast, yet simple adaptation is that general interaction dynamics between agents and objects are fixed, and only object-specific preferences are updated. Our adaptation occurs online, requires only one human intervention (one-shot), and produces new behaviors never seen during training. Trained on cheap synthetic data instead of expensive human demonstrations, our policy correctly adapts to human perturbations on realistic tasks on a physical 7DOF robot. Videos, code, and supplementary material are provided.

Zhimeng Jiang, Kaixiong Zhou, Mi Zhang et al.

Real-time bidding (RTB) has become a major paradigm of display advertising. Each ad impression generated from a user visit is auctioned in real time, where demand-side platform (DSP) automatically provides bid price usually relying on the ad impression value estimation and the optimal bid price determination. However, the current bid strategy overlooks large randomness of the user behaviors (e.g., click) and the cost uncertainty caused by the auction competition. In this work, we explicitly factor in the uncertainty of estimated ad impression values and model the risk preference of a DSP under a specific state and market environment via a sequential decision process. Specifically, we propose a novel adaptive risk-aware bidding algorithm with budget constraint via reinforcement learning, which is the first to simultaneously consider estimation uncertainty and the dynamic risk tendency of a DSP. We theoretically unveil the intrinsic relation between the uncertainty and the risk tendency based on value at risk (VaR). Consequently, we propose two instantiations to model risk tendency, including an expert knowledge-based formulation embracing three essential properties and an adaptive learning method based on self-supervised reinforcement learning. We conduct extensive experiments on public datasets and show that the proposed framework outperforms state-of-the-art methods in practical settings.

Weiye Zhao, Yifan Sun, Feihan Li et al.

Due to the trial-and-error nature, it is typically challenging to apply RL algorithms to safety-critical real-world applications, such as autonomous driving, human-robot interaction, robot manipulation, etc, where such errors are not tolerable. Recently, safe RL (i.e. constrained RL) has emerged rapidly in the literature, in which the agents explore the environment while satisfying constraints. Due to the diversity of algorithms and tasks, it remains difficult to compare existing safe RL algorithms. To fill that gap, we introduce GUARD, a Generalized Unified SAfe Reinforcement Learning Development Benchmark. GUARD has several advantages compared to existing benchmarks. First, GUARD is a generalized benchmark with a wide variety of RL agents, tasks, and safety constraint specifications. Second, GUARD comprehensively covers state-of-the-art safe RL algorithms with self-contained implementations. Third, GUARD is highly customizable in tasks and algorithms. We present a comparison of state-of-the-art safe RL algorithms in various task settings using GUARD and establish baselines that future work can build on.

Yanan Wang, Yong Ge, Li Li et al.

Reinforcement learning (RL) has shown great promise in optimizing long-term user interest in recommender systems. However, existing RL-based recommendation methods need a large number of interactions for each user to learn a robust recommendation policy. The challenge becomes more critical when recommending to new users who have a limited number of interactions. To that end, in this paper, we address the cold-start challenge in the RL-based recommender systems by proposing a meta-level model-based reinforcement learning approach for fast user adaptation. In our approach, we learn to infer each user's preference with a user context variable that enables recommendation systems to better adapt to new users with few interactions. To improve adaptation efficiency, we learn to recover the user policy and reward from only a few interactions via an inverse reinforcement learning method to assist a meta-level recommendation agent. Moreover, we model the interaction relationship between the user model and recommendation agent from an information-theoretic perspective. Empirical results show the effectiveness of the proposed method when adapting to new users with only a single interaction sequence. We further provide a theoretical analysis of the recommendation performance bound.

Xi Liu, Li Li, Ping-Chun Hsieh et al.

With the explosive growth of online products and content, recommendation techniques have been considered as an effective tool to overcome information overload, improve user experience, and boost business revenue. In recent years, we have observed a new desideratum of considering long-term rewards of multiple related recommendation tasks simultaneously. The consideration of long-term rewards is strongly tied to business revenue and growth. Learning multiple tasks simultaneously could generally improve the performance of individual task due to knowledge sharing in multi-task learning. While a few existing works have studied long-term rewards in recommendations, they mainly focus on a single recommendation task. In this paper, we propose {\it PoDiRe}: a \underline{po}licy \underline{di}stilled \underline{re}commender that can address long-term rewards of recommendations and simultaneously handle multiple recommendation tasks. This novel recommendation solution is based on a marriage of deep reinforcement learning and knowledge distillation techniques, which is able to establish knowledge sharing among different tasks and reduce the size of a learning model. The resulting model is expected to attain better performance and lower response latency for real-time recommendation services. In collaboration with Samsung Game Launcher, one of the world's largest commercial mobile game platforms, we conduct a comprehensive experimental study on large-scale real data with hundreds of millions of events and show that our solution outperforms many state-of-the-art methods in terms of several standard evaluation metrics.

Rui Chen, Wenshuo Wang, Zirui Zhao et al.

One typical assumption in inverse reinforcement learning (IRL) is that human experts act to optimize the expected utility of a stochastic cost with a fixed distribution. This assumption deviates from actual human behaviors under ambiguity. Risk-sensitive inverse reinforcement learning (RS-IRL) bridges such gap by assuming that humans act according to a random cost with respect to a set of subjectively distorted distributions instead of a fixed one. Such assumption provides the additional flexibility to model human's risk preferences, represented by a risk envelope, in safe-critical tasks. However, like other learning from demonstration techniques, RS-IRL could also suffer inefficient learning due to redundant demonstrations. Inspired by the concept of active learning, this research derives a probabilistic disturbance sampling scheme to enable an RS-IRL agent to query expert support that is likely to expose unrevealed boundaries of the expert's risk envelope. Experimental results confirm that our approach accelerates the convergence of RS-IRL algorithms with lower variance while still guaranteeing unbiased convergence.