Related papers: LAVA: Latent Action Spaces via Variational Auto-en…
Cross-lingual adaptation has proven effective in spoken language understanding (SLU) systems with limited resources. Existing methods are frequently unsatisfactory for intent detection and slot filling, particularly for distant languages…
Aiming at efficient and dense chain-of-thought (CoT) reasoning, latent reasoning methods fine-tune Large Language Models (LLMs) to substitute discrete language tokens with continuous latent tokens. These methods consume fewer tokens…
Recently, there has been increasing interest in transparency and interpretability in Deep Reinforcement Learning (DRL) systems. Verbal explanations, as the most natural way of communication in our daily life, deserve more attention, since…
Vision-Language-Action (VLA) models often suffer from performance degradation under distribution shifts, as they struggle to learn generalized behavior representations across varying environments. While existing approaches attempt to…
Reinforcement learning~(RL) is a versatile framework for learning to solve complex real-world tasks. However, influences on the learning performance of RL algorithms are often poorly understood in practice. We discuss different analysis…
Real-world autonomous decision-making systems, from robots to recommendation engines, must operate in environments that change over time. While deep reinforcement learning (RL) has shown an impressive ability to learn optimal policies in…
In this work, we evaluate the effectiveness of representation learning approaches for decision making in visually complex environments. Representation learning is essential for effective reinforcement learning (RL) from high-dimensional…
Reinforcement learning (RL) often encounters delayed and sparse feedback in real-world applications, even with only episodic rewards. Previous approaches have made some progress in reward redistribution for credit assignment but still face…
Reinforcement learning (RL) has become a pivotal component of large language model (LLM) post-training, and agentic RL extends this paradigm to operate as agents through multi-turn interaction and tool use. Scaling such systems exposes two…
The rapid progress of auto-regressive vision-language models (VLMs) has inspired growing interest in vision-language-action models (VLA) for robotic manipulation. Recently, masked diffusion models, a paradigm distinct from autoregressive…
In this paper we consider self-supervised representation learning to improve sample efficiency in reinforcement learning (RL). We propose a forward prediction objective for simultaneously learning embeddings of states and action sequences.…
Learning-based vehicle planning is receiving increasing attention with the emergence of diverse driving simulators and large-scale driving datasets. While offline reinforcement learning (RL) is well suited for these safety-critical tasks,…
Reinforcement learning (RL) is a framework to optimize a control policy using rewards that are revealed by the system as a response to a control action. In its standard form, RL involves a single agent that uses its policy to accomplish a…
We propose a novel reinforcement learning (RL) design to optimize the charging strategy for autonomous mobile robots in large-scale block stacking warehouses. RL design involves a wide array of choices that can mostly only be evaluated…
Vision-Language-Action (VLA) models show promise for robotic control, yet performance in complex household environments remains sub-optimal. Mobile manipulation requires reasoning about global scene layout, fine-grained geometry, and…
Open-domain dialog generation is a challenging problem; maximum likelihood training can lead to repetitive outputs, models have difficulty tracking long-term conversational goals, and training on standard movie or online datasets may lead…
Humans face countless scenarios that require reasoning and judgment in daily life. However, existing large language model training methods primarily allow models to learn from existing textual content or solve predetermined problems,…
Vision-Language-Action (VLA) models enable robots to understand and perform complex tasks from multimodal input. Although recent work explores using reinforcement learning (RL) to automate the laborious data collection process in scaling…
This paper describes a purely data-driven solution to a class of sequential decision-making problems with a large number of concurrent online decisions, with applications to computing systems and operations research. We assume that while…
The success of Reinforcement Learning (RL) heavily relies on the ability to learn robust representations from the observations of the environment. In most cases, the representations learned purely by the reinforcement learning loss can…