相关论文: CoinRun: Solving Goal Misgeneralisation

A core challenge in the development of increasingly capable AI systems is to make them safe and reliable by ensuring their behaviour is consistent with human values. This challenge, known as the alignment problem, does not merely apply to…

Zero-shot human-AI coordination holds the promise of collaborating with humans without human data. Prevailing methods try to train the ego agent with a population of partners via self-play. However, these methods suffer from two problems:…

Recent advances in deep learning have brought attention to the possibility of creating advanced, general AI systems that outperform humans across many tasks. However, if these systems pursue unintended goals, there could be catastrophic…

Motion retargeting is a promising approach for generating natural and compelling animations for nonhuman characters. However, it is challenging to translate human movements into semantically equivalent motions for target characters with…

Given the ubiquitous nature of numbers in text, reasoning with numbers to perform simple calculations is an important skill of AI systems. While many datasets and models have been developed to this end, state-of-the-art AI systems are…

Since Alan Turing envisioned Artificial Intelligence (AI) [1], a major driving force behind technical progress has been competition with human cognition. Historical milestones have been frequently associated with computers matching or…

In this article we introduce the Arcade Learning Environment (ALE): both a challenge problem and a platform and methodology for evaluating the development of general, domain-independent AI technology. ALE provides an interface to hundreds…

The goal of minimizing misclassification error on a training set is often just one of several real-world goals that might be defined on different datasets. For example, one may require a classifier to also make positive predictions at some…

Helping people identify and pursue personally meaningful career goals at scale remains a key challenge in applied psychology. Career coaching can improve goal quality and attainment, but its cost and limited availability restrict access.…

Since the earliest proposals for artificial neural network (ANN) models of the mind and brain, critics have pointed out key weaknesses in these models compared to human cognitive abilities. Here we review recent work that uses metalearning…

In the pursuit of artificial general intelligence (AGI), we tackle Abstraction and Reasoning Corpus (ARC) tasks using a novel two-pronged approach. We employ the Decision Transformer in an imitation learning paradigm to model human…

Goal misalignment, reward sparsity and difficult credit assignment are only a few of the many issues that make it difficult for deep reinforcement learning (RL) agents to learn optimal policies. Unfortunately, the black-box nature of deep…

For artificial intelligence to be beneficial to humans the behaviour of AI agents needs to be aligned with what humans want. In this paper we discuss some behavioural issues for language agents, arising from accidental misspecification by…

The value-alignment problem for artificial intelligence (AI) asks how we can ensure that the 'values' (i.e., objective functions) of artificial systems are aligned with the values of humanity. In this paper, I argue that linguistic…

We introduce WebGames, a comprehensive benchmark suite designed to evaluate general-purpose web-browsing AI agents through a collection of 50+ interactive challenges. These challenges are specifically crafted to be straightforward for…

The increasing capabilities of artificial intelligence (AI) systems make it ever more important that we interpret their internals to ensure that their intentions are aligned with human values. Yet there is reason to believe that misaligned…

One of the challenges facing artificial intelligence research today is designing systems capable of utilizing systematic reasoning to generalize to new tasks. The Abstraction and Reasoning Corpus (ARC) measures such a capability through a…

We introduce AlphaRank, an artificial intelligence approach to address the fixed-budget ranking and selection (R&S) problems. We formulate the sequential sampling decision as a Markov decision process and propose a Monte Carlo…

A key value proposition of machine learning is generalizability: the same methods and model architecture should be able to work across different domains and different contexts. While powerful, this generalization can sometimes go too far,…

A variety of cooperative multi-agent control problems require agents to achieve individual goals while contributing to collective success. This multi-goal multi-agent setting poses difficulties for recent algorithms, which primarily target…