Related papers: Reinforcing Language Agents via Policy Optimizatio…

Existing action detection algorithms usually generate action proposals through an extensive search over the video at multiple temporal scales, which brings about huge computational overhead and deviates from the human perception procedure.…

One of the preeminent obstacles to scaling multi-agent reinforcement learning to large numbers of agents is assigning credit to individual agents' actions. In this paper, we address this credit assignment problem with an approach that we…

Reinforcement Learning has emerged as a promising framework for developing adaptive and data-driven strategies, enabling market makers to optimize decision-making policies based on interactions with the limit order book environment. This…

Proximal Policy Optimization (PPO) has become the de facto standard for training legged robots, thanks to its robustness and scalability in massively parallel simulation environments like IsaacLab. However, its on-policy nature makes it…

In the intrinsically motivated skills acquisition problem, the agent is set in an environment without any pre-defined goals and needs to acquire an open-ended repertoire of skills. To do so the agent needs to be autotelic (deriving from the…

Developing a universal and versatile embodied intelligence system presents two primary challenges: the critical embodied data bottleneck, where real-world data is scarce and expensive, and the algorithmic inefficiency of existing methods,…

When observing the actions of others, humans make inferences about why they acted as they did, and what this implies about the world; humans also use the fact that their actions will be interpreted in this manner, allowing them to act…

The role of reinforcement learning (RL) in enhancing the reasoning of large language models (LLMs) is becoming increasingly significant. Despite the success of RL in many scenarios, there are still many challenges in improving the reasoning…

Preference optimization (PO) is indispensable for large language models (LLMs), with methods such as direct preference optimization (DPO) and proximal policy optimization (PPO) achieving great success. A common belief is that DPO is…

Large language model (LLM) agents have emerged as powerful tools for complex tasks, yet their ability to adapt to individual users remains fundamentally limited. We argue this limitation stems from a critical architectural conflation:…

To learn directed behaviors in complex environments, intelligent agents need to optimize objective functions. Various objectives are known for designing artificial agents, including task rewards and intrinsic motivation. However, it is…

Language models trained on large amounts of data are known to produce inappropriate content in some cases and require careful tuning to be used in the real world. We revisit an effective and modular approach for controllability of the…

A multitude of industries depend on accurate and reasonable tabular data augmentation for their business processes. Contemporary methodologies in generating tabular data revolve around utilizing Generative Adversarial Networks (GAN) or…

Asynchronous reinforcement learning improves rollout throughput for large language model agents by decoupling sample generation from policy optimization, but it also introduces a critical failure mode for PPO-style off-policy correction. In…

Existing reinforcement learning (RL) approaches treat large language models (LLMs) as a unified policy, overlooking their internal mechanisms. In this paper, we decompose the LLM-based policy into Internal Layer Policies and Internal…

Collaborative multi-agent exploration of unknown environments is crucial for search and rescue operations. Effective real-world deployment must address challenges such as limited inter-agent communication and static and dynamic obstacles.…

Most prior works on communication in multi-agent reinforcement learning have focused on emergent communication, which often results in inefficient and non-interpretable systems. Inspired by the role of language in natural intelligence, we…

Understanding an agent's goals helps explain and predict its behaviour, yet there is no established methodology for reliably attributing goals to agentic systems. We propose a framework for evaluating goal-directedness that integrates…

Proficient game agents with diverse play styles enrich the gaming experience and enhance the replay value of games. However, recent advancements in game AI based on reinforcement learning have predominantly focused on improving proficiency,…

Decomposition methods have been proposed to approximate solutions to large sequential decision making problems. In contexts where an agent interacts with multiple entities, utility decomposition can be used to separate the global objective…