Related papers: Learned Belief Search: Efficiently Improving Polic…

Recent superhuman results in games have largely been achieved in a variety of zero-sum settings, such as Go and Poker, in which agents need to compete against others. However, just like humans, real-world AI systems have to coordinate and…

Reinforcement learning in partially observable environments is typically challenging, as it requires agents to learn an estimate of the underlying system state. These challenges are exacerbated in multi-agent settings, where agents learn…

We present a novel LLM-informed model-based planning framework, and a novel prompt selection method, for object search in partially-known environments. Our approach uses an LLM to estimate statistics about the likelihood of finding the…

Methods for learning to search for structured prediction typically imitate a reference policy, with existing theoretical guarantees demonstrating low regret compared to that reference. This is unsatisfactory in many applications where the…

Cooperative games are those in which both agents share the same payoff structure. Value-based reinforcement-learning algorithms, such as variants of Q-learning, have been applied to learning cooperative games, but they only apply when the…

Cooperative games are those in which both agents share the same payoff structure. Value-based reinforcement-learning algorithms, such as variants of Q-learning, have been applied to learning cooperative games, but they only apply when the…

Many important robotics problems are partially observable in the sense that a single visual or force-feedback measurement is insufficient to reconstruct the state. Standard approaches involve learning a policy over beliefs or…

In this paper, we propose a test-time adaptive agent that performs exploratory inference through posterior-guided belief refinement without relying on gradient-based updates or additional training for LLM agent operating under partial…

Planning in real-world settings often entails addressing partial observability while aligning with users' requirements. We present a novel framework for expressing users' constraints and preferences about agent behavior in a partially…

Reinforcement learning from verifiable rewards (RLVR) is a promising paradigm for improving large language model (LLM) agents on long-horizon interactive tasks. However, in partially observable environments, incomplete observations cause…

Online decision making under uncertainty in partially observable domains, also known as Belief Space Planning, is a fundamental problem in robotics and Artificial Intelligence. Due to an abundance of plausible future unravelings,…

Large Language Models (LLMs) have facilitated structured data generation, with applications in domains like tabular data, document databases, product catalogs, etc. However, concerns persist about generation veracity due to incorrect…

Large language models (LLMs) are increasingly deployed on long-horizon tasks in partially observable environments, where they must act while inferring and tracking a complex environment state over many steps. This leads to two challenges:…

Lookahead search has been a critical component of recent AI successes, such as in the games of chess, go, and poker. However, the search methods used in these games, and in many other settings, are tabular. Tabular search methods do not…

Information gathering in a partially observable environment can be formulated as a reinforcement learning (RL), problem where the reward depends on the agent's uncertainty. For example, the reward can be the negative entropy of the agent's…

Humans achieve efficient learning by relying on prior knowledge about the structure of naturally occurring tasks. There is considerable interest in designing reinforcement learning (RL) algorithms with similar properties. This includes…

We present Neural Bayesian Filtering (NBF), an algorithm for maintaining distributions over hidden states, called beliefs, in partially observable systems. NBF is trained to find a good latent representation of the beliefs induced by a…

Deciding how to act in partially observable environments remains an active area of research. Identifying good sequences of decisions is particularly challenging when good control performance requires planning multiple steps into the future…

Unsupervised representation learning has succeeded with excellent results in many applications. It is an especially powerful tool to learn a good representation of environments with partial or noisy observations. In partially observable…

Reinforcement Learning (RL) traditionally relies on scalar reward signals, limiting its ability to leverage the rich semantic knowledge often available in real-world tasks. In contrast, humans learn efficiently by combining numerical…