Related papers: Safety Aware Reinforcement Learning (SARL)

To achieve general intelligence, agents must learn how to interact with others in a shared environment: this is the challenge of multiagent reinforcement learning (MARL). The simplest form is independent reinforcement learning (InRL), where…

In recent years, significant progress has been made in the field of robotic reinforcement learning (RL), enabling methods that handle complex image observations, train in the real world, and incorporate auxiliary data, such as…

Safety is critical when applying reinforcement learning (RL) to real-world problems. As a result, safe RL has emerged as a fundamental and powerful paradigm for optimizing an agent's policy while incorporating notions of safety. A prevalent…

This paper addresses the challenges of training end-to-end autonomous driving agents using Reinforcement Learning (RL). RL agents are typically trained in a fixed set of scenarios and nominal behavior of surrounding road users in…

Online reinforcement learning in complex tasks is time-consuming, as massive interaction steps are needed to learn the optimal Q-function.Vision-language action (VLA) policies represent a promising direction for solving diverse tasks;…

Multi-agent reinforcement learning (MARL) has achieved notable success in cooperative tasks, demonstrating impressive performance and scalability. However, deploying MARL agents in real-world applications presents critical safety…

Autonomous driving has attracted significant research interests in the past two decades as it offers many potential benefits, including releasing drivers from exhausting driving and mitigating traffic congestion, among others. Despite…

Reinforcement learning can train LLM agents from sparse task rewards, but long-horizon credit assignment remains challenging: a single success-or-failure signal must be distributed across many actions. Existing methods rely on…

Effective interactive tool use requires agents to master Tool Integrated Reasoning (TIR): a complex process involving multi-turn planning and long-context dialogue management. To train agents for this dynamic process, particularly in…

This paper presents a novel approach to Multi-Agent Reinforcement Learning (MARL) that combines cooperative task decomposition with the learning of reward machines (RMs) encoding the structure of the sub-tasks. The proposed method helps…

Recently, deep multi-agent reinforcement learning (MARL) has shown the promise to solve complex cooperative tasks. Its success is partly because of parameter sharing among agents. However, such sharing may lead agents to behave similarly…

In many real-world applications, safety constraints for reinforcement learning (RL) algorithms are either unknown or not explicitly defined. We propose a framework that concurrently learns safety constraints and optimal RL policies in such…

In edge computing systems, autonomous agents must make fast local decisions while competing for shared resources. Existing MARL methods often resume to centralized critics or frequent communication, which fail under limited observability…

Reinforcement Learning (RL) in various decision-making tasks of machine learning provides effective results with an agent learning from a stand-alone reward function. However, it presents unique challenges with large amounts of environment…

LLM-based multi-agent systems excel at planning, tool use, and role coordination, but their openness and interaction complexity also expose them to jailbreak, prompt-injection, and adversarial collaboration. Existing defenses fall into two…

Deep multi-agent reinforcement learning (MARL) has been demonstrated effectively in simulations for multi-robot problems. For autonomous vehicles, the development of vehicle-to-vehicle (V2V) communication technologies provide opportunities…

Despite recent advances in reinforcement learning (RL), its application in safety critical domains like autonomous vehicles is still challenging. Although punishing RL agents for risky situations can help to learn safe policies, it may also…

The large-scale integration of intermittent renewable energy resources introduces increased uncertainty and volatility to the supply side of power systems, thereby complicating system operation and control. Recently, data-driven approaches,…

Methods that extract policy primitives from offline demonstrations using deep generative models have shown promise at accelerating reinforcement learning(RL) for new tasks. Intuitively, these methods should also help to trainsafeRLagents…

Lane change decision-making is a complex task due to intricate vehicle-vehicle and vehicle-infrastructure interactions. Existing algorithms for lane-change control often depend on vehicles with a certain level of autonomy (e.g., autonomous…