Related papers: A Versatile Agent for Fast Learning from Human Ins…

Research on robotic manipulation has developed a diverse set of policy paradigms, including vision-language-action (VLA) models, vision-action (VA) policies, and code-based compositional approaches. Concrete policies typically attain high…

In this article we study the problem of training intelligent agents using Reinforcement Learning for the purpose of game development. Unlike systems built to replace human players and to achieve super-human performance, our agents aim to…

Modern AI systems such as self-driving cars and game-playing agents achieve superhuman performance, but often lack human-like generalization, interpretability, and inter-operability with human users. Inspired by the rich interactions…

Developing agents that can quickly adapt their behavior to new tasks remains a challenge. Meta-learning has been applied to this problem, but previous methods require either specifying a reward function which can be tedious or providing…

We explore a collaborative and cooperative multi-agent reinforcement learning setting where a team of reinforcement learning agents attempt to solve a single cooperative task in a multi-scenario setting. We propose a novel multi-agent…

Multitask learning poses significant challenges due to the highly multimodal and diverse nature of robot action distributions. However, effectively fitting policies to these complex task distributions is often difficult, and existing…

In this work we propose an approach to learn a robust policy for solving the pivoting task. Recently, several model-free continuous control algorithms were shown to learn successful policies without prior knowledge of the dynamics of the…

Solving complex problems using reinforcement learning necessitates breaking down the problem into manageable tasks and learning policies to solve these tasks. These policies, in turn, have to be controlled by a master policy that takes…

Large language model (LLM)-based agents that reason, plan, and act through tools, memory, and structured interaction are emerging as a promising paradigm for automating complex workflows. Recent systems such as OpenClaw and Claude Code…

The tasks that an agent will need to solve often are not known during training. However, if the agent knows which properties of the environment are important then, after learning how its actions affect those properties, it may be able to…

In explainable artificial intelligence, there is increasing interest in understanding the behaviour of autonomous agents to build trust and validate performance. Modern agent architectures, such as those trained by deep reinforcement…

Mixed cooperative-competitive control scenarios such as human-machine interaction with individual goals of the interacting partners are very challenging for reinforcement learning agents. In order to contribute towards intuitive…

Robotic systems are ever more capable of automation and fulfilment of complex tasks, particularly with reliance on recent advances in intelligent systems, deep learning and artificial intelligence. However, as robots and humans come closer…

The "small agent, big world" frame offers a conceptual view that motivates the need for continual learning. The idea is that a small agent operating in a much bigger world cannot store all information that the world has to offer. To perform…

Imitation learning enables autonomous agents to learn from human examples, without the need for a reward signal. Still, if the provided dataset does not encapsulate the task correctly, or when the task is too complex to be modeled, such…

Fast expansion of natural language functionality of intelligent virtual agents is critical for achieving engaging and informative interactions. However, developing accurate models for new natural language domains is a time and data…

Lifelong machine learning methods acquire knowledge over a series of consecutive tasks, continually building upon their experience. Current lifelong learning algorithms rely upon a single learning agent that has centralized access to all…

Multi-agent AI systems have proven effective for complex reasoning. These systems are compounded by specialized agents, which collaborate through explicit communication, but incur substantial computational overhead. A natural question…

Advances in reinforcement learning (RL) often rely on massive compute resources and remain notoriously sample inefficient. In contrast, the human brain is able to efficiently learn effective control strategies using limited resources. This…

The subject of this paper is reinforcement learning. Policies are considered here that produce actions based on states and random elements autocorrelated in subsequent time instants. Consequently, an agent learns from experiments that are…