Related papers: Learned Belief Search: Efficiently Improving Polic…

Real-world planning problems, including autonomous driving and sustainable energy applications like carbon storage and resource exploration, have recently been modeled as partially observable Markov decision processes (POMDPs) and solved…

Many real-world decision problems involve the interaction of multiple self-interested agents with limited sensing ability. The partially observable stochastic game (POSG) provides a mathematical framework for modeling these problems,…

In social learning, a network of agents assigns probability scores (beliefs) to some hypotheses of interest, which rule the generation of local streaming data observed by each agent. Belief formation takes place by means of an iterative…

Large Reasoning Models (LRMs) have demonstrated remarkable performance on complex tasks but suffer from high computational costs and latency. While selective thinking strategies improve efficiency by routing easy queries to non-thinking…

This paper investigates the automatic exploration problem under the unknown environment, which is the key point of applying the robotic system to some social tasks. The solution to this problem via stacking decision rules is impossible to…

This paper investigates search in model-based reinforcement learning (RL). Conventional wisdom holds that long-term predictions and compounding errors are the primary obstacles for model-based RL. We challenge this view, showing that search…

Recent Offline Reinforcement Learning methods have succeeded in learning high-performance policies from fixed datasets of experience. A particularly effective approach learns to first identify and then mimic optimal decision-making…

We study offline reinforcement learning (RL) which seeks to learn a good policy based on a fixed, pre-collected dataset. A fundamental challenge behind this task is the distributional shift due to the dataset lacking sufficient exploration,…

We study Reinforcement Learning for partially observable dynamical systems using function approximation. We propose a new \textit{Partially Observable Bilinear Actor-Critic framework}, that is general enough to include models such as…

Deep reinforcement learning has enabled human-level or even super-human performance in various types of games. However, the amount of exploration required for learning is often quite large. Deep reinforcement learning also has super-human…

Large language models (LLMs) have recently achieved remarkable results in complex multi-step tasks, such as mathematical reasoning and agentic software engineering. However, they often struggle to maintain consistent performance across…

This paper studies offline policy learning, which aims at utilizing observations collected a priori (from either fixed or adaptively evolving behavior policies) to learn an optimal individualized decision rule that achieves the best overall…

Reinforcement learning (RL) is a goal-oriented learning solution that has proven to be successful for Neural Architecture Search (NAS) on the CIFAR and ImageNet datasets. However, a limitation of this approach is its high computational…

Test-time scaling (TTS) has become an effective approach for improving large language model performance by allocating additional computation during inference. However, existing TTS strategies are largely hand-crafted: researchers manually…

Model-based Reinforcement Learning estimates the true environment through a world model in order to approximate the optimal policy. This family of algorithms usually benefits from better sample efficiency than their model-free counterparts.…

In the drug discovery process, where experiments can be costly and time-consuming, computational models that predict drug-target interactions are valuable tools to accelerate the development of new therapeutic agents. Estimating the…

Efficient inference for wide output layers (WOLs) is an essential yet challenging task in large scale machine learning. Most approaches reduce this problem to approximate maximum inner product search (MIPS), which relies heavily on the…

Deterministic policies are often preferred over stochastic ones when implemented on physical systems. They can prevent erratic and harmful behaviors while being easier to implement and interpret. However, in practice, exploration is largely…

Reward engineering is an important aspect of reinforcement learning. Whether or not the user's intentions can be correctly encapsulated in the reward function can significantly impact the learning outcome. Current methods rely on manually…

In practical applications, we can rarely assume full observability of a system's environment, despite such knowledge being important for determining a reactive control system's precise interaction with its environment. Therefore, we propose…