Related papers: HRM-Agent: Training a recurrent reasoning model in…

Reward models play a critical role in guiding large language models toward outputs that align with human expectations. However, an open challenge remains in effectively utilizing test-time compute to enhance reward model performance. In…

Reinforcement learning (RL) is a branch of machine learning which is employed to solve various sequential decision making problems without proper supervision. Due to the recent advancement of deep learning, the newly proposed Deep-RL…

Model based reinforcement learning has proven to be more sample efficient than model free methods. On the other hand, the construction of a dynamics model in model based reinforcement learning has increased complexity. Data processing tasks…

Reinforcement Learning (RL) agents often struggle in sparse-reward environments where traditional exploration strategies fail to discover effective action sequences. Large Language Models (LLMs) possess procedural knowledge and reasoning…

A key method for creating Artificial Intelligence (AI) agents is Reinforcement Learning (RL). However, constructing a standalone RL policy that maps perception to action directly encounters severe problems, chief among them being its lack…

Large Language Model (LLM)-based agents exhibit significant potential across various domains, operating as interactive systems that process environmental observations to generate executable actions for target tasks. The effectiveness of…

One of the key challenges in applying reinforcement learning to real-life problems is that the amount of train-and-error required to learn a good policy increases drastically as the task becomes complex. One potential solution to this…

Can emergent language models faithfully model the intelligence of decision-making agents? Though modern language models exhibit already some reasoning ability, and theoretically can potentially express any probable distribution over tokens,…

Achieving safe and coordinated behavior in dynamic, constraint-rich environments remains a major challenge for learning-based control. Pure end-to-end learning often suffers from poor sample efficiency and limited reliability, while…

An inverse reinforcement learning (IRL) agent learns to act intelligently by observing expert demonstrations and learning the expert's underlying reward function. Although learning the reward functions from demonstrations has achieved great…

Reinforcement learning often uses neural networks to solve complex control tasks. However, neural networks are sensitive to input perturbations, which makes their deployment in safety-critical environments challenging. This work lifts…

Recent research has turned to Reinforcement Learning (RL) to solve challenging decision problems, as an alternative to hand-tuned heuristics. RL can learn good policies without the need for modeling the environment's dynamics. Despite this…

Hierarchical reinforcement learning (HRL) is a promising approach to extend traditional reinforcement learning (RL) methods to solve more complex tasks. Yet, the majority of current HRL methods require careful task-specific design and…

In model-based reinforcement learning, the agent interleaves between model learning and planning. These two components are inextricably intertwined. If the model is not able to provide sensible long-term prediction, the executed planner…

Reinforcement learning (RL) has produced spectacular results in games, robotics, and continuous control. Yet, despite these successes, learned policies often fail to generalize beyond their training distribution, limiting real-world impact.…

Large language models excel at short-horizon reasoning tasks, but performance drops as reasoning horizon lengths increase. Existing approaches to combat this rely on inference-time scaffolding or costly step-level supervision, neither of…

Recurrent meta reinforcement learning (meta-RL) agents are agents that employ a recurrent neural network (RNN) for the purpose of "learning a learning algorithm". After being trained on a pre-specified task distribution, the learned weights…

Reinforcement learning (RL) agents aim at learning by interacting with an environment, and are not designed for representing or reasoning with declarative knowledge. Knowledge representation and reasoning (KRR) paradigms are strong in…

Reinforcement learning (RL) studies how an agent comes to achieve reward in an environment through interactions over time. Recent advances in machine RL have surpassed human expertise at the world's oldest board games and many classic video…

Hierarchical Reasoning Model (HRM) is a novel approach using two small neural networks recursing at different frequencies. This biologically inspired method beats Large Language models (LLMs) on hard puzzle tasks such as Sudoku, Maze, and…