Related papers: Avoiding Wireheading with Value Reinforcement Lear…
Real-world reinforcement learning (RL) environments, whether in robotics or industrial settings, often involve non-visual observations and require not only efficient but also reliable and thus interpretable and flexible RL approaches. To…
In reinforcement learning (RL), sparse rewards are a natural way to specify the task to be learned. However, most RL algorithms struggle to learn in this setting since the learning signal is mostly zeros. In contrast, humans are good at…
The potential of reinforcement learning (RL) to deliver aligned and performant agents is partially bottlenecked by the reward engineering problem. One alternative to heuristic trial-and-error is preference-based RL (PbRL), where a reward…
Active Reinforcement Learning (ARL) is a twist on RL where the agent observes reward information only if it pays a cost. This subtle change makes exploration substantially more challenging. Powerful principles in RL like optimism, Thompson…
Hierarchical Reinforcement Learning (HRL) is well-suitedd for solving complex tasks by breaking them down into structured policies. However, HRL agents often struggle with efficient exploration and quick adaptation. To overcome these…
Inverse reinforcement learning (IRL) deals with estimating an agent's utility function from its actions. In this paper, we consider how an agent can hide its strategy and mitigate an adversarial IRL attack; we call this inverse IRL (I-IRL).…
Reinforcement Learning with Rubric Rewards (RLRR) is a framework that extends conventional reinforcement learning from human feedback (RLHF) and verifiable rewards (RLVR) by replacing scalar preference signals with structured,…
Inverse reinforcement learning (IRL) is an imitation learning approach to learning reward functions from expert demonstrations. Its use avoids the difficult and tedious procedure of manual reward specification while retaining the…
The aim of inverse reinforcement learning (IRL) is to infer an agent's preferences from observing their behaviour. Usually, preferences are modelled as a reward function, $R$, and behaviour is modelled as a policy, $\pi$. One of the central…
Designing effective reward functions remains a fundamental challenge in reinforcement learning (RL), as it often requires extensive human effort and domain expertise. While RL from human feedback has been successful in aligning agents with…
Reward shaping allows reinforcement learning (RL) agents to accelerate learning by receiving additional reward signals. However, these signals can be difficult to design manually, especially for complex RL tasks. We propose a simple and…
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…
In this work, we study an inverse reinforcement learning (IRL) problem where the experts are planning under a shared reward function but with different, unknown planning horizons. Without the knowledge of discount factors, the reward…
Conveying complex objectives to reinforcement learning (RL) agents can often be difficult, involving meticulous design of reward functions that are sufficiently informative yet easy enough to provide. Human-in-the-loop RL methods allow…
Humans are spectacular reinforcement learners, constantly learning from and adjusting to experience and feedback. Unfortunately, this doesn't necessarily mean humans are fast learners. When tasks are challenging, learning can become…
Envisioned application areas for reinforcement learning (RL) include autonomous driving, precision agriculture, and finance, which all require RL agents to make decisions in the real world. A significant challenge hindering the adoption of…
Reinforcement learning (RL) has become a standard paradigm for refining large language models (LLMs) beyond pre-training and instruction tuning. A prominent line of work is RL with verifiable rewards (RLVR), which leverages automatically…
Interactive adaptive systems powered by Reinforcement Learning (RL) have many potential applications, such as intelligent tutoring systems. In such systems there is typically an external human system designer that is creating, monitoring…
Offline reinforcement learning (RL) provides a powerful framework for training robotic agents using pre-collected, suboptimal datasets, eliminating the need for costly, time-consuming, and potentially hazardous online interactions. This is…
Reinforcement Learning (RL) algorithms can suffer from poor sample efficiency when rewards are delayed and sparse. We introduce a solution that enables agents to learn temporally extended actions at multiple levels of abstraction in a…