相关论文: Modelling non-reinforced preferences using selecti…

To integrate into human-centered environments, autonomous agents must learn from and adapt to humans in their native settings. Preference-based reinforcement learning (PbRL) can enable this by learning reward functions from human…

Personalized AI-based services involve a population of individual reinforcement learning agents. However, most reinforcement learning algorithms focus on harnessing individual learning and fail to leverage the social learning capabilities…

Many sequential decision-making tasks involve optimizing multiple conflicting objectives, requiring policies that adapt to different user preferences. In multi-objective reinforcement learning (MORL), one widely studied approach} addresses…

Preference-based Reinforcement Learning (PbRL) is a paradigm in which an RL agent learns to optimize a task using pair-wise preference-based feedback over trajectories, rather than explicit reward signals. While PbRL has demonstrated…

User behavior modeling lies at the heart of personalized applications like recommender systems. With LLM-based agents, user preference representation has evolved from latent embeddings to semantic memory. While existing memory mechanisms…

Exploration is a prerequisite for learning useful behaviors in sparse-reward, long-horizon tasks, particularly within 3D environments. Curiosity-driven reinforcement learning addresses this via intrinsic rewards derived from the mismatch…

We study the problem of learning exploration-exploitation strategies that effectively adapt to dynamic environments, where the task may change over time. While RNN-based policies could in principle represent such strategies, in practice…

Reward engineering and designing an incentive reward function are non-trivial tasks to train agents in complex environments. Furthermore, an inaccurate reward function may lead to a biased behaviour which is far from an efficient and…

Machine unlearning refers to the process of mitigating the influence of specific training data on machine learning models based on removal requests from data owners. However, one important area that has been largely overlooked in the…

Preference-based reinforcement learning (PbRL) is an approach that enables RL agents to learn from preference, which is particularly useful when formulating a reward function is challenging. Existing PbRL methods generally involve a…

A fundamental challenge in multiagent reinforcement learning is to learn beneficial behaviors in a shared environment with other simultaneously learning agents. In particular, each agent perceives the environment as effectively…

Temporal abstraction in reinforcement learning is the ability of an agent to learn and use high-level behaviors, called options. The option-critic architecture provides a gradient-based end-to-end learning method to construct options. We…

Machine learning systems embed preferences either in training losses or through post-processing of calibrated predictions. Applying information design methods from Strack and Yang (2024), this paper provides decision problem agnostic…

This paper introduces a new imitation learning framework based on energy-based generative models capable of learning complex, physics-dependent, robot motion policies through state-only expert motion trajectories. Our algorithm, called…

Autonomously learning diverse behaviors without an extrinsic reward signal has been a problem of interest in reinforcement learning. However, the nature of learning in such mechanisms is unconstrained, often resulting in the accumulation of…

Building autonomous -- i.e., choosing goals based on one's needs -- and adaptive -- i.e., surviving in ever-changing environments -- agents has been a holy grail of artificial intelligence (AI). A living organism is a prime example of such…

Human drivers exhibit individual preferences regarding driving style. Adapting autonomous vehicles to these preferences is essential for user trust and satisfaction. However, existing end-to-end driving approaches often rely on predefined…

We propose to learn to distinguish reversible from irreversible actions for better informed decision-making in Reinforcement Learning (RL). From theoretical considerations, we show that approximate reversibility can be learned through a…

Reward-free, unsupervised discovery of skills is an attractive alternative to the bottleneck of hand-designing rewards in environments where task supervision is scarce or expensive. However, current skill pre-training methods, like many RL…

Many real-world reinforcement learning problems have a hierarchical nature, and often exhibit some degree of partial observability. While hierarchy and partial observability are usually tackled separately (for instance by combining…