Related papers: Learning CLI Agents with Structured Action Credit …

Reinforcement learning (RL) agents improve through trial-and-error, but when reward is sparse and the agent cannot discover successful action sequences, learning stagnates. This has been a notable problem in training deep RL agents to…

Graphical User Interface (GUI) agents have emerged as a promising paradigm for intelligent systems that perceive and interact with graphical interfaces visually. Yet supervised fine-tuning alone cannot handle long-horizon credit assignment,…

Agentic reinforcement learning (RL) for Large Language Models (LLMs) critically depends on the exploration capability of the base policy, as training signals emerge only within its in-capability region. For tasks where the base policy…

Reinforcement learning (RL) for large language models (LLMs) increasingly relies on sparse, outcome-level rewards -- yet determining which actions within a long trajectory caused the outcome remains difficult. This credit assignment (CA)…

As large language model (LLM) agents evolve from isolated tool users into coordinated teams, reinforcement learning (RL) must optimize not only individual actions but also how work is spawned, delegated, communicated, aggregated, and…

In environments with sparse or delayed rewards, reinforcement learning (RL) incurs high sample complexity due to the large number of interactions needed for learning. This limitation has motivated the use of large language models (LLMs) for…

As autonomous agents become adept at understanding and interacting with graphical user interface (GUI) environments, a new era of automated task execution is emerging. Recent studies have demonstrated that Reinforcement Learning (RL) can…

While reinforcement learning (RL) has achieved notable success in various domains, training effective policies for complex tasks remains challenging. Agents often converge to local optima and fail to maximize long-term rewards. Existing…

Building trust in reinforcement learning (RL) agents requires understanding why they make certain decisions, especially in high-stakes applications like robotics, healthcare, and finance. Existing explainability methods often focus on…

We present a multi-agent actor-critic method that aims to implicitly address the credit assignment problem under fully cooperative settings. Our key motivation is that credit assignment among agents may not require an explicit formulation…

This paper presents an approach for accelerated learning of optimal plans for a given task represented using Linear Temporal Logic (LTL) in multi-agent systems. Given a set of options (temporally abstract actions) available to each agent,…

Traditional multi-agent reinforcement learning (MARL) algorithms, such as independent Q-learning, struggle when presented with partially observable scenarios, and where agents are required to develop delicate action sequences. This is often…

Recent work in AI safety has highlighted that in sequential decision making, objectives are often underspecified or incomplete. This gives discretion to the acting agent to realize the stated objective in ways that may result in undesirable…

Existing agents for solving tasks such as ML engineering rely on prompting powerful language models. As a result, these agents do not improve with more experience. In this paper, we show that agents backed by weaker models that improve via…

Reward design is a key component of deep reinforcement learning, yet some tasks and designer's objectives may be unnatural to define as a scalar cost function. Among the various techniques, formal methods integrated with DRL have garnered…

Credit assignment, the process of attributing credit or blame to individual agents for their contributions to a team's success or failure, remains a fundamental challenge in multi-agent reinforcement learning (MARL), particularly in…

Graphical User Interface (GUI) agents have demonstrated remarkable progress in automating complex user interface interactions through reinforcement learning. However, current approaches face a fundamental dilemma: offline RL enables stable…

With the rapid advancements in Large Language Models (LLMs), an increasing number of studies have leveraged LLMs as the cognitive core of agents to address complex task decision-making challenges. Specially, recent research has demonstrated…

Reinforcement Learning (RL) faces significant challenges in adaptive healthcare interventions, such as dementia care, where data is scarce, decisions require interpretability, and underlying patient-state dynamic are complex and causal in…

Reinforcement learning systems rely on environment interfaces that specify observations and reward functions, yet constructing these interfaces for new tasks often requires substantial manual effort. While recent work has automated reward…