相关论文: SAINT: Attention-Based Policies for Discrete Combi…

Meta-reinforcement learning enables artificial agents to learn from related training tasks and adapt to new tasks efficiently with minimal interaction data. However, most existing research is still limited to narrow task distributions that…

Transformers are widely used in natural language processing, where they consistently achieve state-of-the-art performance. This is mainly due to their attention-based architecture, which allows them to model rich linguistic relations…

When learning policies for real-world domains, two important questions arise: (i) how to efficiently use pre-collected off-policy, non-optimal behavior data; and (ii) how to mediate among different competing objectives and constraints. We…

The networked nature of multi-robot systems presents challenges in the context of multi-agent reinforcement learning. Centralized control policies do not scale with increasing numbers of robots, whereas independent control policies do not…

Action understanding, encompassing action detection and anticipation, plays a crucial role in numerous practical applications. However, untrimmed videos are often characterized by substantial redundant information and noise. Moreover, in…

In multiagent systems (MASs), each agent makes individual decisions but all of them contribute globally to the system evolution. Learning in MASs is difficult since each agent's selection of actions must take place in the presence of other…

User interests are usually dynamic in the real world, which poses both theoretical and practical challenges for learning accurate preferences from rich behavior data. Among existing user behavior modeling solutions, attention networks are…

In this paper, we consider groups of agents in a network that select actions in order to satisfy a set of constraints that vary arbitrarily over time and minimize a time-varying function of which they have only local observations. The…

Reinforcement learning (RL) with combinatorial action spaces remains challenging because feasible action sets are exponentially large and governed by complex feasibility constraints, making direct policy parameterization impractical.…

Learning agent behaviors from observational data has shown to improve our understanding of their decision-making processes, advancing our ability to explain their interactions with the environment and other agents. While multiple learning…

This article presents a novel multi-agent spatial transformer (MAST) for learning communication policies in large-scale decentralized and collaborative multi-robot systems (DC-MRS). Challenges in collaboration in DC-MRS arise from: (i)…

Behavioral changes in animals and humans, as a consequence of an error or a verbal instruction, can be extremely rapid. Improvement in behavioral performances are usually associated in machine learning and reinforcement learning to synaptic…

Recent breakthroughs in Go play and strategic games have witnessed the great potential of reinforcement learning in intelligently scheduling in uncertain environment, but some bottlenecks are also encountered when we generalize this…

Reinforcement learning agents that operate in diverse and complex environments can benefit from the structured decomposition of their behavior. Often, this is addressed in the context of hierarchical reinforcement learning, where the aim is…

While reinforcement learning has achieved remarkable successes in several domains, its real-world application is limited due to many methods failing to generalise to unfamiliar conditions. In this work, we consider the problem of…

Building generalist agents that can rapidly adapt to new environments is a key challenge for deploying AI in the digital and real worlds. Is scaling current agent architectures the most effective way to build generalist agents? We propose a…

An agent's functionality is largely determined by its design, i.e., skeletal structure and joint attributes (e.g., length, size, strength). However, finding the optimal agent design for a given function is extremely challenging since the…

Sequential Recommenders, which exploit dynamic user intents through interaction sequences, is vulnerable to adversarial attacks. While existing attacks primarily rely on data poisoning, they require large-scale user access or fake profiles…

Despite success in many challenging problems, reinforcement learning (RL) is still confronted with sample inefficiency, which can be mitigated by introducing prior knowledge to agents. However, many transfer techniques in reinforcement…

The Transformer, a highly expressive architecture for sequence modeling, has recently been adapted to solve sequential decision-making, most notably through the Decision Transformer (DT), which learns policies by conditioning on desired…