Related papers: Model-Free RL Agents Demonstrate System 1-Like Int…

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…

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…

Reinforcement learning (RL) is an appealing paradigm for training intelligent agents, enabling policy acquisition from the agent's own autonomously acquired experience. However, the training process of RL is far from automatic, requiring…

Inferring a person's goal from their behavior is an important problem in applications of AI (e.g. automated assistants, recommender systems). The workhorse model for this task is the rational actor model - this amounts to assuming that…

How should an agent decide when and how to plan? A dominant approach builds agents as reactive policies with adaptive computation (e.g., chain-of-thought), trained end-to-end expecting planning to emerge implicitly. Without control over the…

We present the first mechanistic evidence that model-free reinforcement learning agents can learn to plan. This is achieved by applying a methodology based on concept-based interpretability to a model-free agent in Sokoban -- a commonly…

Autonomous vehicles inevitably encounter a vast array of scenarios in real-world environments. Addressing long-tail scenarios, particularly those involving intensive interactions with numerous traffic participants, remains one of the most…

Planning methods can solve temporally extended sequential decision making problems by composing simple behaviors. However, planning requires suitable abstractions for the states and transitions, which typically need to be designed by hand.…

Recent work on large language models has demonstrated the use of model-free reinforcement learning (RL) to train reasoning-like capabilities. The emergence of "thinking" through model-free RL is interesting as thinking actions neither…

We introduce an architecture for studying the behavior of large language model (LLM) agents in the absence of externally imposed tasks. Our continuous reason and act framework, using persistent memory and self-feedback, enables sustained…

As reinforcement learning agents become increasingly deployed in real-world scenarios, predicting future agent actions and events during deployment is important for facilitating better human-agent interaction and preventing catastrophic…

Model-free reinforcement learning (RL) is inherently a reactive method, operating under the assumption that it starts with no prior knowledge of the system and entirely depends on trial-and-error for learning. This approach faces several…

When learning to behave in a stochastic environment where safety is critical, such as driving a vehicle in traffic, it is natural for human drivers to plan fallback strategies as a backup to use if ever there is an unexpected change in the…

Recent advances in theoretical biology suggest that basal cognition and sentient behaviour are emergent properties of in vitro cell cultures and neuronal networks, respectively. Such neuronal networks spontaneously learn structured…

This paper proposes a low-cost, easily realizable strategy to equip a reinforcement learning (RL) agent the capability of behaving ethically. Our model allows the designers of RL agents to solely focus on the task to achieve, without having…

Large Language Models (LLMs) trained with reinforcement learning and verifiable rewards have achieved strong results on complex reasoning tasks. Recent work extends this paradigm to a multi-agent setting, where a meta-thinking agent…

Most of agents that learn policy for tasks with reinforcement learning (RL) lack the ability to communicate with people, which makes human-agent collaboration challenging. We believe that, in order for RL agents to comprehend utterances…

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…

Unlike reinforcement learning (RL) agents, humans remain capable multitaskers in changing environments. In spite of only experiencing the world through their own observations and interactions, people know how to balance focusing on tasks…

We consider communication when there is no agreement about symbols and meanings. We treat it within the framework of reinforcement learning. We apply different reinforcement learning models in our studies and simplify the problem as much as…