Related papers: Continual and Multi-task Reinforcement Learning Wi…

Multi-task learning is to improve the performance of the model by transferring and exploiting common knowledge among tasks. Existing MTL works mainly focus on the scenario where label sets among multiple tasks (MTs) are usually the same,…

Learning to predict multiple attributes of a pedestrian is a multi-task learning problem. To share feature representation between two individual task networks, conventional methods like Cross-Stitch and Sluice network learn a linear…

In cooperative multi-agent reinforcement learning, a collection of agents learns to interact in a shared environment to achieve a common goal. We propose the use of reward machines (RM) -- Mealy machines used as structured representations…

Many potential applications of reinforcement learning in the real world involve interacting with other agents whose numbers vary over time. We propose new neural policy architectures for these multi-agent problems. In contrast to other…

Continual learning is the problem of learning new tasks or knowledge while protecting old knowledge and ideally generalizing from old experience to learn new tasks faster. Neural networks trained by stochastic gradient descent often degrade…

Modern language agents must operate over long-horizon, multi-turn interactions, where they retrieve external information, adapt to observations, and answer interdependent queries. Yet, most LLM systems rely on full-context prompting,…

This paper focuses on the data-insufficiency problem in multi-task learning within an episodic training setup. Specifically, we explore the potential of heterogeneous information across tasks and meta-knowledge among episodes to effectively…

The ability to pick up on language signals in an ongoing interaction is crucial for future machine learning models to collaborate and interact with humans naturally. In this paper, we present an initial study that evaluates intra-episodic…

Sharing parameters in multi-agent deep reinforcement learning has played an essential role in allowing algorithms to scale to a large number of agents. Parameter sharing between agents significantly decreases the number of trainable…

Growing neuropsychological and neurophysiological evidence suggests that the visual cortex uses parts-based representations to encode, store and retrieve relevant objects. In such a scheme, objects are represented as a set of spatially…

Continual Learning, also known as Lifelong Learning, aims to continually learn from new data as it becomes available. While prior research on continual learning in automatic speech recognition has focused on the adaptation of models across…

When do machine learning systems fail to generalize, and what mechanisms could improve their generalization? Here, we draw inspiration from cognitive science to argue that one weakness of parametric machine learning systems is their failure…

Most reinforcement learning algorithms are inefficient for learning multiple tasks in complex robotic systems, where different tasks share a set of actions. In such environments a compound policy may be learnt with shared neural network…

Deep reinforcement learning has been applied successfully to solve various real-world problems and the number of its applications in the multi-agent settings has been increasing. Multi-agent learning distinctly poses significant challenges…

We investigate the effects of multi-task learning using the recently introduced task of semantic tagging. We employ semantic tagging as an auxiliary task for three different NLP tasks: part-of-speech tagging, Universal Dependency parsing,…

Parameter sharing, as an important technique in multi-agent systems, can effectively solve the scalability issue in large-scale agent problems. However, the effectiveness of parameter sharing largely depends on the environment setting. When…

Robots and autonomous systems require an understanding of complex events (CEs) from sensor data to interact with their environments and humans effectively. Traditional end-to-end neural architectures, despite processing sensor data…

Tasks where the set of possible actions depend discontinuously on the state pose a significant challenge for current reinforcement learning algorithms. For example, a locked door must be first unlocked, and then the handle turned before the…

While humans and animals learn incrementally during their lifetimes and exploit their experience to solve new tasks, standard deep reinforcement learning methods specialize to solve only one task at a time. As a result, the information they…

Large language models (LLMs) have achieved impressive linguistic capabilities. However, a key limitation persists in their lack of human-like memory faculties. LLMs exhibit constrained memory retention across sequential interactions,…