Search

Fairness in classification tasks has traditionally focused on bias removal from neural representations, but recent trends favor algorithmic methods that embed fairness into the training process. These methods steer models towards fair performance, preventing potential elimination of valuable information that arises from representation manipulation. Reinforcement Learning (RL), with its capacity for learning through interaction and adjusting reward functions to encourage desired behaviors, emerges as a promising tool in this domain. In this paper, we explore the usage of RL to address bias in imbalanced classification by scaling the reward function to mitigate bias. We employ the contextual multi-armed bandit framework and adapt three popular RL algorithms to suit our objectives, demonstrating a novel approach to mitigating bias.

We develop an artificial agent motivated to augment its knowledge base beyond its initial training. The agent actively participates in dialogues with other agents, strategically acquiring new information. The agent models its knowledge as an RDF knowledge graph, integrating new beliefs acquired through conversation. Responses in dialogue are generated by identifying graph patterns around these new integrated beliefs. We show that policies can be learned using reinforcement learning to select effective graph patterns during an interaction, without relying on explicit user feedback. Within this context, our study is a proof of concept for leveraging users as effective sources of information.

Improving sample efficiency is central to Reinforcement Learning (RL), especially in environments where the rewards are sparse. Some recent approaches have proposed to specify reward functions as manually designed or learned reward structures whose integrations in the RL algorithms are claimed to significantly improve the learning efficiency. Manually designed reward structures can suffer from inaccuracy and existing automatically learning methods are often computationally intractable for complex tasks. The integration of inaccurate or partial reward structures in RL algorithms fail to learn optimal policies. In this work, we propose an RL algorithm that can automatically structure the reward function for sample efficiency, given a set of labels that signify subtasks. Given such minimal knowledge about the task, we train a high-level policy that selects optimal sub-tasks in each state together with a low-level policy that efficiently learns to complete each sub-task. We evaluate our algorithm in a variety of sparse-reward environments. The experiment results show that our approach significantly outperforms the state-of-art baselines as the difficulty of the task increases.

Nowadays, social media plays an important role in many fields, such as the promotion of measures against major infectious diseases, merchandising, etc. In social media, some people are known as opinion leaders due to their strong ability to influence the opinions of others. The detection of opinion leaders has become an important task in social network analysis. Social networks are often represented in the form of graphs which allows a large number of graph analysis methods to be used for opinion leader detection. Some studies have attempted to apply graph representation learning for opinion leader detection and achieved good results. In this paper, we propose a model-agnostic framework that formulate the opinion leader detection problem as a ranking task of node embeddings. A variety of methods and datasets are chosen to analyze the performance of our framework both qualitatively and quantitatively. Based on the analysis results, we propose a strategy that combines opinion leaders detected by two different ranking algorithms to obtain a more comprehensive set of opinion leaders. And we analyze the temporal changes of the opinion leaders in one of the dynamic social networks.

Training a dialogue policy using deep reinforcement learning requires a lot of exploration of the environment. The amount of wasted invalid exploration makes their learning inefficient. In this paper, we find and define an important reason for the invalid exploration: dead-ends. When a conversation enters a dead-end state, regardless of the actions taken afterward, it will continue in a dead-end trajectory until the agent reaches a termination state or maximum turn. We propose a dead-end resurrection (DDR) algorithm that detects the initial dead-end state in a timely and efficient manner and provides a rescue action to guide and correct the exploration direction. To prevent dialogue policies from repeatedly making the same mistake, DDR also performs dialogue data augmentation by adding relevant experiences containing dead-end states. We first validate the dead-end detection reliability and then demonstrate the effectiveness and generality of the method by reporting experimental results on several dialogue datasets from different domains.

Communication is an effective mechanism for coordinating the behavior of multiple agents. In the field of multi-agent reinforcement learning, agents can improve the overall learning performance and achieve their objectives by communication. Moreover, agents can communicate various types of messages, either to all agents or to specific agent groups, and through specific channels. With the growing body of research work in MARL with communication (Comm-MARL), there is lack of a systematic and structural approach to distinguish and classify existing Comm-MARL systems. In this paper, we survey recent works in the Comm-MARL field and consider various aspects of communication that can play a role in the design and development of multi-agent reinforcement learning systems. With these aspects in mind, we propose several dimensions along which Comm-MARL systems can be analyzed, developed, and compared., Comment: 10 pages, 4 figures, 10 tables