相关论文: Goal Misgeneralization in Deep Reinforcement Learn…

Reinforcement Learning (RL) has become the de facto standard for tuning LLMs to solve tasks involving reasoning. However, growing evidence shows that models trained in such way often suffer from a significant loss in diversity. We argue…

Model-based Reinforcement Learning (MBRL) aims to make agents more sample-efficient, adaptive, and explainable by learning an explicit model of the environment. While the capabilities of MBRL agents have significantly improved in recent…

Campbell-Goodhart's law relates to the causal inference error whereby decision-making agents aim to influence variables which are correlated to their goal objective but do not reliably cause it. This is a well known error in Economics and…

To date, distributional reinforcement learning (distributional RL) methods have exclusively focused on the discounted setting, where an agent aims to optimize a discounted sum of rewards over time. In this work, we extend distributional RL…

Current reinforcement learning (RL) often suffers when solving a challenging exploration problem where the desired outcomes or high rewards are rarely observed. Even though curriculum RL, a framework that solves complex tasks by proposing a…

Reinforcement learning (RL) research focuses on general solutions that can be applied across different domains. This results in methods that RL practitioners can use in almost any domain. However, recent studies often lack the engineering…

Reinforcement Learning algorithms are primarily focused on learning a policy that maximizes expected return. As a result, the learned policy can exploit one or few reward sources. However, in many natural situations, it is desirable to…

We introduce a new notion of generalization -- Distributional Generalization -- which roughly states that outputs of a classifier at train and test time are close *as distributions*, as opposed to close in just their average error. For…

The Overfitted Brain hypothesis suggests dreams happen to allow generalization in the human brain. Here, we ask if the same is true for reinforcement learning agents as well. Given limited experience in a real environment, we use…

One of the key reasons for the high sample complexity in reinforcement learning (RL) is the inability to transfer knowledge from one task to another. In standard multi-task RL settings, low-reward data collected while trying to solve one…

Offline reinforcement learning (RL) provides a promising approach to avoid costly online interaction with the real environment. However, the performance of offline RL highly depends on the quality of the datasets, which may cause…

In this paper, we hypothesize that internal function sharing is one of the reasons to weaken o.o.d. or systematic generalization in deep learning for classification tasks. Under equivalent prediction, a model partitions an input space into…

Generalization remains a challenging problem for deep reinforcement learning algorithms, which are often trained and tested on the same set of deterministic game environments. When test environments are unseen and perturbed but the nature…

Most known regret bounds for reinforcement learning are either episodic or assume an environment without traps. We derive a regret bound without making either assumption, by allowing the algorithm to occasionally delegate an action to an…

Continual learning (CL), which aims to learn a sequence of tasks, has attracted significant recent attention. However, most work has focused on the experimental performance of CL, and theoretical studies of CL are still limited. In…

This work introduces a neuro-symbolic agent that combines deep reinforcement learning (DRL) with temporal logic (TL) to achieve systematic zero-shot, i.e., never-seen-before, generalisation of formally specified instructions. In particular,…

In Multi-Goal Reinforcement Learning, an agent learns to achieve multiple goals with a goal-conditioned policy. During learning, the agent first collects the trajectories into a replay buffer, and later these trajectories are selected…

To achieve general intelligence, agents must learn how to interact with others in a shared environment: this is the challenge of multiagent reinforcement learning (MARL). The simplest form is independent reinforcement learning (InRL), where…

In this lecture, we present a general perspective on reinforcement learning (RL) objectives, where we show three versions of objectives. The first version is the standard definition of objective in RL literature. Then we extend the standard…

Reinforcement Learning (RL) based solutions are being adopted in a variety of domains including robotics, health care and industrial automation. Most focus is given to when these solutions work well, but they fail when presented with out of…