VickreyFeedback: Cost-efficient Data Construction for Reinforcement Learning from Human Feedback

This paper addresses the cost-efficiency aspect of Reinforcement Learning from Human Feedback (RLHF). RLHF leverages datasets of human preferences over outputs of large language models (LLM) to instill human expectations into LLMs. While preference annotation comes with a monetized cost, the economic utility of a preference dataset has not been considered by far. What exacerbates this situation is that given complex intransitive or cyclic relationships in preference datasets, existing algorithms for fine-tuning LLMs are still far from capturing comprehensive preferences. This raises severe cost-efficiency concerns in production environments, where preference data accumulate over time. In this paper, we see the fine-tuning of LLMs as a monetized economy and introduce an auction mechanism to improve the efficiency of the preference data collection in dollar terms. We show that introducing an auction mechanism can play an essential role in enhancing the cost-efficiency of RLHF while maintaining satisfactory model performance. Experimental results demonstrate that our proposed auction-based protocol is cost-efficient for fine-tuning LLMs by concentrating on high-quality feedback.

INSIGHT: End-to-End Neuro-Symbolic Visual Reinforcement Learning with Language Explanations

Neuro-symbolic reinforcement learning (NS-RL) has emerged as a promising paradigm for explainable decision-making, characterized by the interpretability of symbolic policies. For tasks with visual observations, NS-RL entails structured representations for states, but previous algorithms are unable to refine the structured states with reward signals due to a lack of efficiency. Accessibility is also an issue, as extensive domain knowledge is required to interpret current symbolic policies. In this paper, we present a framework that is capable of learning structured states and symbolic policies simultaneously, whose key idea is to overcome the efficiency bottleneck by distilling vision foundation models into a scalable perception module. Moreover, we design a pipeline that uses large language models to generate concise and readable language explanations for policies and decisions. In experiments on nine Atari tasks, our approach demonstrates substantial performance gains over existing NSRL methods. We also showcase explanations for policies and decisions.

Online Policy Learning from Offline Preferences

In preference-based reinforcement learning (PbRL), a reward function is learned from a type of human feedback called preference. To expedite preference collection, recent works have leveraged \emph{offline preferences}, which are preferences collected for some offline data. In this scenario, the learned reward function is fitted on the offline data. If a learning agent exhibits behaviors that do not overlap with the offline data, the learned reward function may encounter generalizability issues. To address this problem, the present study introduces a framework that consolidates offline preferences and \emph{virtual preferences} for PbRL, which are comparisons between the agent's behaviors and the offline data. Critically, the reward function can track the agent's behaviors using the virtual preferences, thereby offering well-aligned guidance to the agent. Through experiments on continuous control tasks, this study demonstrates the effectiveness of incorporating the virtual preferences in PbRL.

Estimating Treatment Effects Under Heterogeneous Interference

Treatment effect estimation can assist in effective decision-making in e-commerce, medicine, and education. One popular application of this estimation lies in the prediction of the impact of a treatment (e.g., a promotion) on an outcome (e.g., sales) of a particular unit (e.g., an item), known as the individual treatment effect (ITE). In many online applications, the outcome of a unit can be affected by the treatments of other units, as units are often associated, which is referred to as interference. For example, on an online shopping website, sales of an item will be influenced by an advertisement of its co-purchased item. Prior studies have attempted to model interference to estimate the ITE accurately, but they often assume a homogeneous interference, i.e., relationships between units only have a single view. However, in real-world applications, interference may be heterogeneous, with multi-view relationships. For instance, the sale of an item is usually affected by the treatment of its co-purchased and co-viewed items. We hypothesize that ITE estimation will be inaccurate if this heterogeneous interference is not properly modeled. Therefore, we propose a novel approach to model heterogeneous interference by developing a new architecture to aggregate information from diverse neighbors. Our proposed method contains graph neural networks that aggregate same-view information, a mechanism that aggregates information from different views, and attention mechanisms. In our experiments on multiple datasets with heterogeneous interference, the proposed method significantly outperforms existing methods for ITE estimation, confirming the importance of modeling heterogeneous interference.

On Modeling Long-Term User Engagement from Stochastic Feedback

An ultimate goal of recommender systems is to improve user engagement. Reinforcement learning (RL) is a promising paradigm for this goal, as it directly optimizes overall performance of sequential recommendation. However, many existing RL-based approaches induce huge computational overhead, because they require not only the recommended items but also all other candidate items to be stored. This paper proposes an efficient alternative that does not require the candidate items. The idea is to model the correlation between user engagement and items directly from data. Moreover, the proposed approach consider randomness in user feedback and termination behavior, which are ubiquitous for RS but rarely discussed in RL-based prior work. With online A/B experiments on real-world RS, we confirm the efficacy of the proposed approach and the importance of modeling the two types of randomness.

Behavior Estimation from Multi-Source Data for Offline Reinforcement Learning

Offline reinforcement learning (RL) have received rising interest due to its appealing data efficiency. The present study addresses behavior estimation, a task that lays the foundation of many offline RL algorithms. Behavior estimation aims at estimating the policy with which training data are generated. In particular, this work considers a scenario where the data are collected from multiple sources. In this case, neglecting data heterogeneity, existing approaches for behavior estimation suffers from behavior misspecification. To overcome this drawback, the present study proposes a latent variable model to infer a set of policies from data, which allows an agent to use as behavior policy the policy that best describes a particular trajectory. This model provides with a agent fine-grained characterization for multi-source data and helps it overcome behavior misspecification. This work also proposes a learning algorithm for this model and illustrates its practical usage via extending an existing offline RL algorithm. Lastly, with extensive evaluation this work confirms the existence of behavior misspecification and the efficacy of the proposed model.

Batch Reinforcement Learning from Crowds

A shortcoming of batch reinforcement learning is its requirement for rewards in data, thus not applicable to tasks without reward functions. Existing settings for lack of reward, such as behavioral cloning, rely on optimal demonstrations collected from humans. Unfortunately, extensive expertise is required for ensuring optimality, which hinder the acquisition of large-scale data for complex tasks. This paper addresses the lack of reward in a batch reinforcement learning setting by learning a reward function from preferences. Generating preferences only requires a basic understanding of a task. Being a mental process, generating preferences is faster than performing demonstrations. So preferences can be collected at scale from non-expert humans using crowdsourcing. This paper tackles a critical challenge that emerged when collecting data from non-expert humans: the noise in preferences. A novel probabilistic model is proposed for modelling the reliability of labels, which utilizes labels collaboratively. Moreover, the proposed model smooths the estimation with a learned reward function. Evaluation on Atari datasets demonstrates the effectiveness of the proposed model, followed by an ablation study to analyze the relative importance of the proposed ideas.