Related papers: Null Counterfactual Factor Interactions for Goal-C…

Autonomous agents must often deal with conflicting requirements, such as completing tasks using the least amount of time/energy, learning multiple tasks, or dealing with multiple opponents. In the context of reinforcement learning~(RL),…

Meta reinforcement learning (meta-RL) aims to learn a policy solving a set of training tasks simultaneously and quickly adapting to new tasks. It requires massive amounts of data drawn from training tasks to infer the common structure…

Humans are able to identify a referred visual object in a complex scene via a few rounds of natural language communications. Success communication requires both parties to engage and learn to adapt for each other. In this paper, we…

Driven by recent successes in two-player, zero-sum game solving and playing, artificial intelligence work on games has increasingly focused on algorithms that produce equilibrium-based strategies. However, this approach has been less…

Intent detection, a critical component in task-oriented dialogue (TOD) systems, faces significant challenges in adapting to the rapid influx of integrable tools with complex interrelationships. Existing approaches, such as zero-shot…

Gait is one of the most promising biometrics that aims to identify pedestrians from their walking patterns. However, prevailing methods are susceptible to confounders, resulting in the networks hardly focusing on the regions that reflect…

Oftentimes, environments for sequential decision-making problems can be quite sparse in the provision of evaluative feedback to guide reinforcement-learning agents. In the extreme case, long trajectories of behavior are merely punctuated…

Human-object interaction (HOI) detection plays a key role in high-level visual understanding, facilitating a deep comprehension of human activities. Specifically, HOI detection aims to locate the humans and objects involved in interactions…

Human-Object Interaction (HOI) detection is a fundamental task in high-level human-centric scene understanding. We propose PhraseHOI, containing a HOI branch and a novel phrase branch, to leverage language prior and improve relation…

When deploying Reinforcement Learning (RL) agents into a physical system, we must ensure that these agents are well aware of the underlying constraints. In many real-world problems, however, the constraints are often hard to specify…

The majority of contemporary object-tracking approaches do not model interactions between objects. This contrasts with the fact that objects' paths are not independent: a cyclist might abruptly deviate from a previously planned trajectory…

Inverse Reinforcement Learning (IRL) aims to reconstruct the reward function from expert demonstrations to facilitate policy learning, and has demonstrated its remarkable success in imitation learning. To promote expert-like behavior,…

Consider a prosthetic arm, learning to adapt to its user's control signals. We propose Interaction-Grounded Learning for this novel setting, in which a learner's goal is to interact with the environment with no grounding or explicit reward…

Human-Object Interaction (HOI) detection aims to understand the interactions between humans and objects, which plays a curtail role in high-level semantic understanding tasks. However, most works pursue designing better architectures to…

This paper proposes a combined optimization and learning method for impact-friendly, non-prehensile catching of objects at non-zero velocity. Through a constrained Quadratic Programming problem, the method generates optimal trajectories up…

Reinforcement learning is a promising framework for solving control problems, but its use in practical situations is hampered by the fact that reward functions are often difficult to engineer. Specifying goals and tasks for autonomous…

In task-oriented dialogue scenarios, cross-domain zero-shot slot filling plays a vital role in leveraging source domain knowledge to learn a model with high generalization ability in unknown target domain where annotated data is…

Recent work in Human-Robot Interaction (HRI) has shown that robots can leverage implicit communicative signals from users to understand how they are being perceived during interactions. For example, these signals can be gaze patterns,…

Unsupervised and self-supervised objectives, such as next token prediction, have enabled pre-training generalist models from large amounts of unlabeled data. In reinforcement learning (RL), however, finding a truly general and scalable…

Reinforcement learning (RL) algorithms usually require a substantial amount of interaction data and perform well only for specific tasks in a fixed environment. In some scenarios such as healthcare, however, usually only few records are…