Related papers: Compress to Focus: Efficient Coordinate Compressio…

For many applications of reinforcement learning it can be more convenient to specify both a reward function and constraints, rather than trying to design behavior through the reward function. For example, systems that physically interact…

While large language models (LLMs) have recently made tremendous progress towards solving challenging AI problems, they have done so at increasingly steep computational and API costs. We propose a novel strategy where we combine multiple…

We present Coordinated Proximal Policy Optimization (CoPPO), an algorithm that extends the original Proximal Policy Optimization (PPO) to the multi-agent setting. The key idea lies in the coordinated adaptation of step size during the…

As terminal agents scale to long-horizon, multi-turn workflows, a key bottleneck is not merely limited context length, but the accumulation of noisy terminal observations in the interaction history. Retaining raw observations preserves…

Constrained reinforcement learning has achieved promising progress in safety-critical fields where both rewards and constraints are considered. However, constrained reinforcement learning methods face challenges in striking the right…

Group-advantage-based reinforcement learning methods, such as GRPO and DAPO, have demonstrated strong performance across diverse domains, including mathematical reasoning and text-to-image generation. However, their reliance on sample-level…

Due to practical constraints such as partial observability and limited communication, Centralized Training with Decentralized Execution (CTDE) has become the dominant paradigm in cooperative Multi-Agent Reinforcement Learning (MARL).…

We propose Discrete Consensus-Based Optimization (DCBO), a fully discrete version of the Consensus-Based Optimization (CBO) framework. DCBO is a multi-agent method for the global optimization of possibly non-convex and non-differentiable…

Enterprise AI systems increasingly deploy multiple intelligent agents across mission-critical workflows that must satisfy hard policy constraints, bounded risk exposure, and comprehensive auditability (SOX, HIPAA, GDPR). Existing…

The advent of autonomous agents is transforming interactions with Graphical User Interfaces (GUIs) by employing natural language as a powerful intermediary. Despite the predominance of Supervised Fine-Tuning (SFT) methods in current GUI…

Solving tasks in Reinforcement Learning is no easy feat. As the goal of the agent is to maximize the accumulated reward, it often learns to exploit loopholes and misspecifications in the reward signal resulting in unwanted behavior. While…

Learning adaptive visuomotor policies for embodied agents remains a formidable challenge, particularly when facing cross-embodiment variations such as diverse sensor configurations and dynamic properties. Conventional learning approaches…

This work studies reinforcement learning (RL) in the context of multi-period supply chains subject to constraints, e.g., on production and inventory. We introduce Distributional Constrained Policy Optimization (DCPO), a novel approach for…

To combat the prohibitive communication costs of ``free-for-all" multi-agent systems (MAS), we introduce \textbf{Agent-GSPO}, a framework that directly optimizes for token economy using sequence-level reinforcement learning. Agent-GSPO…

Graphical User Interface (GUI) agents require effective use of historical context to perform sequential navigation tasks. While incorporating past actions and observations can improve decision making, naive use of full history leads to…

Chemical process optimization and control are affected by 1) plant-model mismatch, 2) process disturbances, and 3) constraints for safe operation. Reinforcement learning by policy optimization would be a natural way to solve this due to its…

Training large language models (LLMs) as interactive agents for controlling graphical user interfaces (GUIs) presents a unique challenge to optimize long-horizon action sequences with multimodal feedback from complex environments. While…

Long-horizon agents face the challenge of growing context size during interaction with environment, which degrades the performance and stability. Existing methods typically introduce the external memory module and look up the relevant…

Engagement-optimized adaptive tutoring systems may prioritize short-term behavioral signals over sustained learning outcomes, creating structural incentives for reward hacking in reinforcement learning policies. We formalize this challenge…

In constrained Markov decision processes, enforcing constraints during training is often thought of as decreasing the final return. Recently, it was shown that constraints can be incorporated directly into the policy geometry, yielding an…