Related papers: Act-Observe-Rewrite: Multimodal Coding Agents as I…

Reinforcement learning (RL) agents have shown remarkable performances in various environments, where they can discover effective policies directly from sensory inputs. However, these agents often exploit spurious correlations in the…

Multi-Agent Reinforcement Learning (MARL) considers settings in which a set of coexisting agents interact with one another and their environment. The adaptation and learning of other agents induces non-stationarity in the environment…

Reinforcement learning for agentic multimodal models often suffers from interaction collapse, where models learn to reduce tool usage and multi-turn reasoning, limiting the benefits of agentic behavior. We introduce PyVision-RL, a…

We consider a learning agent in a partially observable environment, with which the agent has never interacted before, and about which it learns both what it can observe and how its actions affect the environment. The agent can learn about…

Multi-agent reinforcement learning focuses on training the behaviors of multiple learning agents that coexist in a shared environment. Recently, MARL models, such as the Multi-Agent Transformer (MAT) and ACtion dEpendent deep Q-learning…

Online question-and-answer (Q\&A) systems based on the Large Language Model (LLM) have progressively diverged from recreational to professional use. This paper proposed a Multi-Agent framework with environmentally reinforcement learning…

The remarkable reasoning capability of large language models (LLMs) stems from cognitive behaviors that emerge through reinforcement with verifiable rewards. This work investigates how to transfer this principle to Multimodal LLMs (MLLMs)…

Learning a perception and reasoning module for robotic assistants to plan steps to perform complex tasks based on natural language instructions often requires large free-form language annotations, especially for short high-level…

We consider the multi-agent reinforcement learning setting with imperfect information in which each agent is trying to maximize its own utility. The reward function depends on the hidden state (or goal) of both agents, so the agents must…

Model-based reinforcement learning (MBRL) techniques have recently yielded promising results for real-world autonomous racing using high-dimensional observations. MBRL agents, such as Dreamer, solve long-horizon tasks by building a world…

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…

Agentic reasoning models trained with multimodal reinforcement learning (MMRL) have become increasingly capable, yet they are almost universally optimized using sparse, outcome-based rewards computed based on the final answers. Richer…

Advances in multi-agent reinforcement learning (MARL) enable sequential decision making for a range of exciting multi-agent applications such as cooperative AI and autonomous driving. Explaining agent decisions is crucial for improving…

In order to flexibly act in an everyday environment, a robotic agent needs a variety of cognitive capabilities that enable it to reason about plans and perform execution recovery. Large language models (LLMs) have been shown to demonstrate…

Robotic manipulation in complex scenes demands precise perception of task-relevant details, yet fixed or suboptimal viewpoints often impair fine-grained perception and induce occlusions, constraining imitation-learned policies. We present…

Language Models and Vision Language Models have recently demonstrated unprecedented capabilities in terms of understanding human intentions, reasoning, scene understanding, and planning-like behaviour, in text form, among many others. In…

Reinforcement Learning with Verifiable Rewards (RLVR) has advanced the reasoning capability of large language models (LLMs), enabling autonomous agents that can conduct effective multi-turn and tool-integrated reasoning. While instructions…

With the rise of artificial intelligence (AI), applying large language models (LLMs) to mathematical problem-solving has attracted increasing attention. Most existing approaches attempt to improve Operations Research (OR) optimization…

One of the great promises of robot learning systems is that they will be able to learn from their mistakes and continuously adapt to ever-changing environments. Despite this potential, most of the robot learning systems today are deployed…

The prototypical approach to reinforcement learning involves training policies tailored to a particular agent from scratch for every new morphology. Recent work aims to eliminate the re-training of policies by investigating whether a…