相关论文: Motif: Intrinsic Motivation from Artificial Intell…
Describing skills in natural language has the potential to provide an accessible way to inject human knowledge about decision-making into an AI system. We present MaestroMotif, a method for AI-assisted skill design, which yields…
Decision-making agents based on pre-trained Large Language Models (LLMs) are increasingly being deployed across various domains of human activity. While their applications are currently rather specialized, several research efforts are…
Large Language Models (LLMs) and Reinforcement Learning (RL) are two powerful approaches for building autonomous agents. However, due to limited understanding of the game environment, agents often resort to inefficient exploration and…
Training large language models (LLMs) for complex reasoning via Reinforcement Learning with Verifiable Rewards (RLVR) is effective but limited by reliance on costly, domain-specific supervision. We explore Reinforcement Learning from…
Large Language Models (LLMs) have demonstrated remarkable capabilities in open-ended text generation tasks. However, the inherent open-ended nature of these tasks implies that there is always room for improvement in the quality of model…
Reward design is a critical part of the application of reinforcement learning, the performance of which strongly depends on how well the reward signal frames the goal of the designer and how well the signal assesses progress in reaching…
Reinforcement learning has emerged as a powerful paradigm for post-training large language models (LLMs) to improve reasoning. Approaches like Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning with Verifiable…
Biological systems often choose actions without an explicit reward signal, a phenomenon known as intrinsic motivation. The computational principles underlying this behavior remain poorly understood. In this study, we investigate an…
Reinforcement Learning has emerged as a strong alternative to solve optimization tasks efficiently. The use of these algorithms highly depends on the feedback signals provided by the environment in charge of informing about how good (or…
Reinforcement learning has been shown to be highly successful at many challenging tasks. However, success heavily relies on well-shaped rewards. Intrinsically motivated RL attempts to remove this constraint by defining an intrinsic reward…
Reinforcement learning algorithms typically struggle in the absence of a dense, well-shaped reward function. Intrinsically motivated exploration methods address this limitation by rewarding agents for visiting novel states or transitions,…
The reinforcement learning research area contains a wide range of methods for solving the problems of intelligent agent control. Despite the progress that has been made, the task of creating a highly autonomous agent is still a significant…
Designing effective reward functions is crucial to training reinforcement learning (RL) algorithms. However, this design is non-trivial, even for domain experts, due to the subjective nature of certain tasks that are hard to quantify…
Reinforcement Learning with Verifiable Rewards~(RLVR) has emerged as a powerful learn-to-reason paradigm for large reasoning models to tackle complex tasks. However, the current RLVR paradigm is still not efficient enough, as it works in a…
The study of exploration in the domain of decision making has a long history but remains actively debated. From the vast literature that addressed this topic for decades under various points of view (e.g., developmental psychology,…
Autonomous artificial agents must be able to learn behaviors in complex environments without humans to design tasks and rewards. Designing these functions for each environment is not feasible, thus, motivating the development of intrinsic…
Games are challenging for Reinforcement Learning~(RL) agents due to their reward-sparsity, as rewards are only obtainable after long sequences of deliberate actions. Intrinsic Motivation~(IM) methods -- which introduce exploration rewards…
For a natural social human-robot interaction, it is essential for a robot to learn the human-like social skills. However, learning such skills is notoriously hard due to the limited availability of direct instructions from people to teach a…
Recent advances in large language models (LLMs) have demonstrated significant progress in performing complex tasks. While Reinforcement Learning from Human Feedback (RLHF) has been effective in aligning LLMs with human preferences, it is…
Large Language Models (LLMs) have demonstrated remarkable creative writing capabilities, yet their substantial computational demands hinder widespread use. Enhancing Small Language Models (SLMs) offers a promising alternative, but current…