Related papers: LiFT: Unsupervised Reinforcement Learning with Fou…

Reinforcement learning (RL) requires either manually specifying a reward function, which is often infeasible, or learning a reward model from a large amount of human feedback, which is often very expensive. We study a more sample-efficient…

A major challenge in the field of education is providing review schedules that present learned items at appropriate intervals to each student so that memory is retained over time. In recent years, attempts have been made to formulate item…

The field of reinforcement learning (RL) is facing increasingly challenging domains with combinatorial complexity. For an RL agent to address these challenges, it is essential that it can plan effectively. Prior work has typically utilized…

Unsupervised reinforcement learning aims to acquire skills without prior goal representations, where an agent automatically explores an open-ended environment to represent goals and learn the goal-conditioned policy. However, this procedure…

Advanced reasoning in LLMs on challenging domains like mathematical reasoning can be tackled using verifiable rewards based reinforced fine-tuning (ReFT). In standard ReFT frameworks, a behavior model generates multiple completions with…

Multi-Agent Reinforcement Learning (MARL) provides a powerful framework for learning coordination in multi-agent systems. However, applying MARL to robotics still remains challenging due to high-dimensional continuous joint action spaces,…

Creating reinforcement learning (RL) agents that are capable of accepting and leveraging task-specific knowledge from humans has been long identified as a possible strategy for developing scalable approaches for solving long-horizon…

The robustness of any machine learning solution is fundamentally bound by the data it was trained on. One way to generalize beyond the original training is through human-informed augmentation of the original dataset; however, it is…

Logistics operators, from battlefield coordinators re-routing airlifts ahead of a storm to warehouse managers juggling late trucks, need to make mission-critical decisions. Prevailing methods for logistics planning such as integer…

For most reinforcement learning approaches, the learning is performed by maximizing an accumulative reward that is expectedly and manually defined for specific tasks. However, in real world, rewards are emergent phenomena from the complex…

Reward engineering has long been a challenge in Reinforcement Learning (RL) research, as it often requires extensive human effort and iterative processes of trial-and-error to design effective reward functions. In this paper, we propose…

Training large language models (LLMs) to act as autonomous agents for multi-turn, long-horizon tasks remains significant challenges in scalability and training efficiency. To address this, we introduce L-Zero (L0), a scalable, end-to-end…

Natural Language Feedback (NLF) is an increasingly popular mechanism for aligning Large Language Models (LLMs) to human preferences. Despite the diversity of the information it can convey, NLF methods are often hand-designed and arbitrary,…

The inherent uncertainty in the environmental transition model of Reinforcement Learning (RL) necessitates a delicate balance between exploration and exploitation. This balance is crucial for optimizing computational resources to accurately…

Training sophisticated agents for optimal decision-making under uncertainty has been key to the rapid development of modern autonomous systems across fields. Notably, model-free reinforcement learning (RL) has enabled decision-making agents…

Exploration is a cornerstone of reinforcement learning (RL). Intrinsic motivation attempts to decouple exploration from external, task-based rewards. However, established approaches to intrinsic motivation that follow general principles…

Generalizable alignment is a core challenge for deploying Large Language Models (LLMs) safely in real-world NLP applications. Current alignment methods, including Reinforcement Learning from Human Feedback (RLHF), often fail to guarantee…

In this work we address the problem of training a Reinforcement Learning agent to follow multiple temporally-extended instructions expressed in Linear Temporal Logic in sub-symbolic environments. Previous multi-task work has mostly relied…

Safe reinforcement learning (RL) agents accomplish given tasks while adhering to specific constraints. Employing constraints expressed via easily-understandable human language offers considerable potential for real-world applications due to…

Reinforcement learning (RL) algorithms typically start tabula rasa, without any prior knowledge of the environment, and without any prior skills. This however often leads to low sample efficiency, requiring a large amount of interaction…