Related papers: Learning When Not to Answer: A Ternary Reward Stru…
One of the challenges in applying reinforcement learning in a complex real-world environment lies in providing the agent with a sufficiently detailed reward function. Any misalignment between the reward and the desired behavior can result…
Standard reward models typically predict scalar scores that fail to capture the multifaceted nature of response quality in non-verifiable domains, such as creative writing or open-ended instruction following. To address this limitation, we…
Generalization to out of distribution tasks in reinforcement learning is a challenging problem. One successful approach improves generalization by conditioning policies on task or environment descriptions that provide information about the…
Large language model alignment via reinforcement learning depends critically on reward function quality. However, static, domain-specific reward models are often costly to train and exhibit poor generalization in out-of-distribution…
While reinforcement learning (RL) has been successful in natural language processing (NLP) domains such as dialogue generation and text-based games, it typically faces the problem of sparse rewards that leads to slow or no convergence.…
Reinforcement learning (RL) systems can be complex and non-interpretable, making it challenging for non-AI experts to understand or intervene in their decisions. This is due in part to the sequential nature of RL in which actions are chosen…
Reinforcement learning (RL) agents improve through trial-and-error, but when reward is sparse and the agent cannot discover successful action sequences, learning stagnates. This has been a notable problem in training deep RL agents to…
When language models (LMs) are trained via reinforcement learning (RL) to generate natural language "reasoning chains", their performance improves on a variety of difficult question answering tasks. Today, almost all successful applications…
Transfer of recent advances in deep reinforcement learning to real-world applications is hindered by high data demands and thus low efficiency and scalability. Through independent improvements of components such as replay buffers or more…
A characteristic of reinforcement learning is the ability to develop unforeseen strategies when solving problems. While such strategies sometimes yield superior performance, they may also result in undesired or even dangerous behavior. In…
Reinforcement Learning from Human Feedback significantly enhances Natural Language Processing by aligning language models with human expectations. A critical factor in this alignment is the strength of reward models used during training.…
Learning reward functions remains the bottleneck to equip a robot with a broad repertoire of skills. Large Language Models (LLM) contain valuable task-related knowledge that can potentially aid in the learning of reward functions. However,…
Agentic Reinforcement Learning (Agentic RL) has achieved notable success in enabling agents to perform complex reasoning and tool use. However, most methods still relies on sparse outcome-based reward for training. Such feedback fails to…
The development of trustworthy conversational information-seeking systems relies on dialogue models that can generate faithful and accurate responses based on relevant knowledge texts. However, two main challenges hinder this task. Firstly,…
When developing reinforcement learning agents, the standard approach is to train an agent to converge to a fixed policy that is as close to optimal as possible for a single fixed reward function. If different agent behaviour is required in…
Large reasoning models (LRMs) have attracted much attention due to their exceptional performance. However, their performance mainly stems from thinking, a long Chain of Thought (CoT), which significantly increase computational overhead. To…
The standard feedback model of reinforcement learning requires revealing the reward of every visited state-action pair. However, in practice, it is often the case that such frequent feedback is not available. In this work, we take a first…
In this paper, we confront the problem of applying reinforcement learning to agents that perceive the environment through many sensors and that can perform parallel actions using many actuators as is the case in complex autonomous robots.…
Recent work (Xu et al., 2020) has suggested that numeral systems in different languages are shaped by a functional need for efficient communication in an information-theoretic sense. Here we take a learning-theoretic approach and show how…
Equipping agents with the capacity to justify made decisions using supporting evidence represents a cornerstone of accountable decision-making. Furthermore, ensuring that justifications are in line with human expectations and societal norms…