Related papers: TRAM: Test-Time Risk Adaptation with Mixture of Ag…

Standard model-based reinforcement learning (MBRL) approaches fit a transition model of the environment to all past experience, but this wastes model capacity on data that is irrelevant for policy improvement. We instead propose a new…

Reward specification plays a central role in reinforcement learning (RL), guiding the agent's behavior. To express non-Markovian rewards, formalisms such as reward machines have been introduced to capture dependencies on histories. However,…

In safety-critical domains, reinforcement learning (RL) agents must often satisfy strict, zero-cost safety constraints while accomplishing tasks. Existing model-free methods frequently either fail to achieve near-zero safety violations or…

In the context of multi-agent reinforcement learning, generalization is a challenge to solve various tasks that may require different joint policies or coordination without relying on policies specialized for each task. We refer to this…

Credit assignmen, disentangling each agent's contribution to a shared reward, is a critical challenge in cooperative multi-agent reinforcement learning (MARL). To be effective, credit assignment methods must preserve the environment's…

Reinforcement learning (RL) is central to post-training, particularly for agentic models that require specialized reasoning behaviors. In this setting, model merging offers a practical mechanism for integrating multiple RL-trained agents…

We use model-free reinforcement learning, extensive simulation, and transfer learning to develop a continuous control algorithm that has good zero-shot performance in a real physical environment. We train a simulated agent to act optimally…

Multi-agent systems have evolved into practical LLM-driven collaborators for many applications, gaining robustness from diversity and cross-checking. However, multi-agent RL (MARL) training is resource-intensive and unstable: co-adapting…

Training a model-free reinforcement learning agent requires allowing the agent to sufficiently explore the environment to search for an optimal policy. In safety-constrained environments, utilizing unsupervised exploration or a non-optimal…

Single-task RL agents are typically trained under a fixed reward function, which limits their robustness to reward misspecification and their ability to adapt to changing preferences. We introduce Reward-Conditioned Reinforcement Learning…

Efficiently adapting to new environments and changes in dynamics is critical for agents to successfully operate in the real world. Reinforcement learning (RL) based approaches typically rely on external reward feedback for adaptation.…

Robotic assembly presents a long-standing challenge due to its requirement for precise, contact-rich manipulation. While simulation-based learning has enabled the development of robust assembly policies, their performance often degrades…

Recently, safe reinforcement learning (RL) with the actor-critic structure for continuous control tasks has received increasing attention. It is still challenging to learn a near-optimal control policy with safety and convergence…

Reinforcement learning (RL) has been used in a range of simulated real-world tasks, e.g., sensor coordination, traffic light control, and on-demand mobility services. However, real world deployments are rare, as RL struggles with dynamic…

Reinforcement learning (RL) has substantially improved the ability of large language model (LLM) agents to interact with environments and solve multi-turn tasks. However, effective agentic RL remains challenging: sparse outcome-only rewards…

The use of Reinforcement Learning (RL) agents in practical applications requires the consideration of suboptimal outcomes, depending on the familiarity of the agent with its environment. This is especially important in safety-critical…

Encountering shifted data at test time is a ubiquitous challenge when deploying predictive models. Test-time adaptation (TTA) methods address this issue by continuously adapting a deployed model using only unlabeled test data. While TTA can…

When developing reinforcement learning agents, the standard approach is to train an agent to converge to a fixed policy that is as close to optimal as possible for a single fixed reward function. If different agent behaviour is required in…

This article proposes a Model Reference Adaptive Control (MRAC) strategy to achieve fixed-time convergence of parameter estimation and tracking errors for unknown linear time-invariant systems, without relying on the persistence of…

Zero-shot coordination problem in multi-agent reinforcement learning (MARL), which requires agents to adapt to unseen agents, has attracted increasing attention. Traditional approaches often rely on the Self-Play (SP) framework to generate…