papers

Publications (112)

cs.LG2022

Quantifying Local Specialization in Deep Neural Networks

Shlomi Hod, Daniel Filan, Stephen Casper +2

A neural network is locally specialized to the extent that parts of its computational graph (i.e. structure) can be abstractly represented as performing some comprehensible sub-tas…

cs.AI2013

Automated Construction of Sparse Bayesian Networks from Unstructured Probabilistic Models and Domain Information

Sampath Srinivas, Stuart Russell, Alice M. Agogino

An algorithm for automated construction of a sparse Bayesian network given an unstructured probabilistic model and causal domain information from an expert has been developed and i…

cs.AI2017

The Off-Switch Game

Dylan Hadfield-Menell, Anca Dragan, Pieter Abbeel +1

It is clear that one of the primary tools we can use to mitigate the potential risk from a misbehaving AI system is the ability to turn the system off. As the capabilities of AI sy…

cs.AI2012

RAPID: A Reachable Anytime Planner for Imprecisely-sensed Domains

Emma Brunskill, Stuart Russell

Despite the intractability of generic optimal partially observable Markov decision process planning, there exist important problems that have highly structured models. Previous res…

cs.CY2025

International AI Safety Report 2025: First Key Update: Capabilities and Risk Implications

Yoshua Bengio, Stephen Clare, Carina Prunkl +70

Since the publication of the first International AI Safety Report, AI capabilities have continued to improve across key domains. New training techniques that teach AI systems to re…

cs.LG2020

DERAIL: Diagnostic Environments for Reward And Imitation Learning

Pedro Freire, Adam Gleave, Sam Toyer +1

The objective of many real-world tasks is complex and difficult to procedurally specify. This makes it necessary to use reward or imitation learning algorithms to infer a reward or…

stat.ML2024

The Effective Horizon Explains Deep RL Performance in Stochastic Environments

Cassidy Laidlaw, Banghua Zhu, Stuart Russell +1

Reinforcement learning (RL) theory has largely focused on proving minimax sample complexity bounds. These require strategic exploration algorithms that use relatively limited funct…

cs.LG2023

Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism

Paria Rashidinejad, Banghua Zhu, Cong Ma +2

Offline (or batch) reinforcement learning (RL) algorithms seek to learn an optimal policy from a fixed dataset without active data collection. Based on the composition of the offli…

cs.LG2023

Invariance in Policy Optimisation and Partial Identifiability in Reward Learning

Joar Skalse, Matthew Farrugia-Roberts, Stuart Russell +2

It is often very challenging to manually design reward functions for complex, real-world tasks. To solve this, one can instead use reward learning to infer a reward function from d…

cs.AI2026

Learning the Preferences of a Learning Agent

Karim Abdel Sadek, Mark Bedaywi, Rhys Gould +1

For AI systems to be useful to humans, they must understand and act in accordance with our values and preferences. Since specifying preferences is a hard task, inverse reinforcemen…

cs.LG2024

When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback

Leon Lang, Davis Foote, Stuart Russell +3

Past analyses of reinforcement learning from human feedback (RLHF) assume that the human evaluators fully observe the environment. What happens when human feedback is based only on…

cs.CL2026

Generalization or Hallucination? Understanding Out-of-Context Reasoning in Transformers

Yixiao Huang, Hanlin Zhu, Tianyu Guo +5

Large language models (LLMs) can acquire new knowledge through fine-tuning, but this process exhibits a puzzling duality: models can generalize remarkably from new facts, yet are a…

cs.NE2021

Clusterability in Neural Networks

Daniel Filan, Stephen Casper, Shlomi Hod +3

The learned weights of a neural network have often been considered devoid of scrutable internal structure. In this paper, however, we look for structure in the form of clusterabili…

cs.AI2012

A temporally abstracted Viterbi algorithm

Shaunak Chatterjee, Stuart Russell

Hierarchical problem abstraction, when applicable, may offer exponential reductions in computational complexity. Previous work on coarse-to-fine dynamic programming (CFDP) has demo…

cs.LG2026

Statistical Guarantees for Offline Domain Randomization

Arnaud Fickinger, Abderrahim Bendahi, Stuart Russell

Reinforcement-learning (RL) agents often struggle when deployed from simulation to the real-world. A dominant strategy for reducing the sim-to-real gap is domain randomization (DR)…

cs.LG2024

Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback

Vincent Conitzer, Rachel Freedman, Jobst Heitzig +9

Foundation models such as GPT-4 are fine-tuned to avoid unsafe or otherwise problematic behavior, such as helping to commit crimes or producing racist text. One approach to fine-tu…

cs.AI2026

Active teacher selection for reward learning

Rachel Freedman, Justin Svegliato, Kyle Wray +1

Reward learning techniques enable machine learning systems to learn objectives from human feedback. A core limitation of these systems is their assumption that all feedback comes f…

cs.LG2012

A Generalized Mean Field Algorithm for Variational Inference in Exponential Families

Eric P. Xing, Michael I. Jordan, Stuart Russell

The mean field methods, which entail approximating intractable probability distributions variationally with distributions from a tractable family, enjoy high efficiency, guaranteed…

cs.LG2018

Learning Plannable Representations with Causal InfoGAN

Thanard Kurutach, Aviv Tamar, Ge Yang +2

In recent years, deep generative models have been shown to 'imagine' convincing high-dimensional observations such as images, audio, and even video, learning directly from raw data…

cs.AI2013

Learning the Structure of Dynamic Probabilistic Networks

Nir Friedman, Kevin Murphy, Stuart Russell

Dynamic probabilistic networks are a compact representation of complex stochastic processes. In this paper we examine how to learn the structure of a DPN from data. We extend struc…

cs.LG2023

Adversarial Policies Beat Superhuman Go AIs

Tony T. Wang, Adam Gleave, Tom Tseng +8

We attack the state-of-the-art Go-playing AI system KataGo by training adversarial policies against it, achieving a >97% win rate against KataGo running at superhuman settings. Our…

cs.LG2013

Rao-Blackwellised Particle Filtering for Dynamic Bayesian Networks

Arnaud Doucet, Nando de Freitas, Kevin Murphy +1

Particle filters (PFs) are powerful sampling-based inference/learning algorithms for dynamic Bayesian networks (DBNs). They allow us to treat, in a principled way, any type of prob…

cs.LG2020

Understanding Learned Reward Functions

Eric J. Michaud, Adam Gleave, Stuart Russell

In many real-world tasks, it is not possible to procedurally specify an RL agent's reward function. In such cases, a reward function must instead be learned from interacting with a…

cs.LG2026

Emergence of Superposition: Unveiling the Training Dynamics of Chain of Continuous Thought

Hanlin Zhu, Shibo Hao, Zhiting Hu +3

Previous work shows that the chain of continuous thought (continuous CoT) improves the reasoning capability of large language models (LLMs) by enabling implicit parallel thinking,…

cs.GT2022

Cooperative and uncooperative institution designs: Surprises and problems in open-source game theory

Andrew Critch, Michael Dennis, Stuart Russell

It is increasingly possible for real-world agents, such as software-based agents or human institutions, to view the internal programming of other such agents that they interact wit…

cs.LG2024

On Representation Complexity of Model-based and Model-free Reinforcement Learning

Hanlin Zhu, Baihe Huang, Stuart Russell

We study the representation complexity of model-based and model-free reinforcement learning (RL) in the context of circuit complexity. We prove theoretically that there exists a br…

cs.LG2025

ALMANACS: A Simulatability Benchmark for Language Model Explainability

Edmund Mills, Shiye Su, Stuart Russell +1

How do we measure the efficacy of language model explainability methods? While many explainability methods have been developed, they are typically evaluated on bespoke tasks, preve…

cs.AI2020

Multi-Principal Assistance Games

Arnaud Fickinger, Simon Zhuang, Dylan Hadfield-Menell +1

Assistance games (also known as cooperative inverse reinforcement learning games) have been proposed as a model for beneficial AI, wherein a robotic agent must act on behalf of a h…

cs.LG2024

Bridging RL Theory and Practice with the Effective Horizon

Cassidy Laidlaw, Stuart Russell, Anca Dragan

Deep reinforcement learning (RL) works impressively in some environments and fails catastrophically in others. Ideally, RL theory should be able to provide an understanding of why…

cs.LG2018

Inverse reinforcement learning for video games

Aaron Tucker, Adam Gleave, Stuart Russell

Deep reinforcement learning achieves superhuman performance in a range of video game environments, but requires that a designer manually specify a reward function. It is often easi…

astro-ph.IM2026

Data-Driven Forecasting of three-Component Seismograms Using Transformer Architectures

Waleed Esmail, Stuart Russell, Jana Klinge +2

Forecasting seismic waveforms beyond observed data remains challenging due to the nonlinear, dispersive, and multi-scale nature of seismic wave propagation. In this work, we introd…

cs.AI2012

Decayed MCMC Filtering

Bhaskara Marthi, Hanna Pasula, Stuart Russell +1

Filtering---estimating the state of a partially observable Markov process from a sequence of observations---is one of the most widely studied problems in control theory, AI, and co…

cs.AI2017

Servant of Many Masters: Shifting priorities in Pareto-optimal sequential decision-making

Andrew Critch, Stuart Russell

It is often argued that an agent making decisions on behalf of two or more principals who have different utility functions should adopt a {\em Pareto-optimal} policy, i.e., a polic…

cs.GT2022

For Learning in Symmetric Teams, Local Optima are Global Nash Equilibria

Scott Emmons, Caspar Oesterheld, Andrew Critch +2

Although it has been known since the 1970s that a globally optimal strategy profile in a common-payoff game is a Nash equilibrium, global optimality is a strict requirement that li…

cs.AI2024

Cooperative Inverse Reinforcement Learning

Dylan Hadfield-Menell, Anca Dragan, Pieter Abbeel +1

For an autonomous system to be helpful to humans and to pose no unwarranted risks, it needs to align its values with those of the humans in its environment in such a way that its a…

cs.LG2024

RL, but don't do anything I wouldn't do

Michael K. Cohen, Marcus Hutter, Yoshua Bengio +1

In reinforcement learning, if the agent's reward differs from the designers' true utility, even only rarely, the state distribution resulting from the agent's policy can be very ba…

cs.AI2016

Swift: Compiled Inference for Probabilistic Programming Languages

Yi Wu, Lei Li, Stuart Russell +1

A probabilistic program defines a probability measure over its semantic structures. One common goal of probabilistic programming languages (PPLs) is to compute posterior probabilit…

cs.LG2023

Active Reward Learning from Multiple Teachers

Peter Barnett, Rachel Freedman, Justin Svegliato +1

Reward learning algorithms utilize human feedback to infer a reward function, which is then used to train an AI system. This human feedback is often a preference comparison, in whi…

cs.LG2026

Transformers Provably Learn to Internalize Chain-of-Thought

Yixiao Huang, Hanlin Zhu, Zixuan Wang +4

Chain-of-Thought (CoT) prompting substantially improves the sample efficiency of transformers, reducing the complexity of tasks like parity learning from exponential to polynomial…

cs.AI2025

Robust and Diverse Multi-Agent Learning via Rational Policy Gradient

Niklas Lauffer, Ameesh Shah, Micah Carroll +3

Adversarial optimization algorithms that explicitly search for flaws in agents' policies have been successfully applied to finding robust and diverse policies in multi-agent settin…

cs.LG2012

Graph partition strategies for generalized mean field inference

Eric P. Xing, Michael I. Jordan, Stuart Russell

An autonomous variational inference algorithm for arbitrary graphical models requires the ability to optimize variational approximations over the space of model parameters as well…

cs.LG2025

Avoiding Catastrophe in Online Learning by Asking for Help

Benjamin Plaut, Hanlin Zhu, Stuart Russell

Most learning algorithms with formal regret guarantees assume that all mistakes are recoverable and essentially rely on trying all possible behaviors. This approach is problematic…

cs.CY2024

Managing extreme AI risks amid rapid progress

Yoshua Bengio, Geoffrey Hinton, Andrew Yao +22

Artificial Intelligence (AI) is progressing rapidly, and companies are shifting their focus to developing generalist AI systems that can autonomously act and pursue goals. Increase…

cs.AI2023

Who Needs to Know? Minimal Knowledge for Optimal Coordination

Niklas Lauffer, Ameesh Shah, Micah Carroll +2

To optimally coordinate with others in cooperative games, it is often crucial to have information about one's collaborators: successful driving requires understanding which side of…

cs.LG2026

Provably Optimal Learning Algorithms for Assistance Games

Nivasini Ananthakrishnan, Mark Bedaywi, Michael I. Jordan +2

This paper studies an online variant of the assistance games framework, where an informed agent and an uninformed agent repeatedly interact over timesteps to optimize a common…

cs.CL2024

Monitoring Latent World States in Language Models with Propositional Probes

Jiahai Feng, Stuart Russell, Jacob Steinhardt

Language models are susceptible to bias, sycophancy, backdoors, and other tendencies that lead to unfaithful responses to the input context. Interpreting internal states of languag…

cs.LG2026

Cross-Domain Imitation Learning via Optimal Transport

Arnaud Fickinger, Samuel Cohen, Stuart Russell +1

Cross-domain imitation learning studies how to leverage expert demonstrations of one agent to train an imitation agent with a different embodiment or morphology. Comparing trajecto…

cs.LG2021

Adversarial Policies: Attacking Deep Reinforcement Learning

Adam Gleave, Michael Dennis, Cody Wild +3

Deep reinforcement learning (RL) policies are known to be vulnerable to adversarial perturbations to their observations, similar to adversarial examples for classifiers. However, a…

cs.LG2012

Efficient Gradient Estimation for Motor Control Learning

Gregory Lawrence, Noah Cowan, Stuart Russell

The task of estimating the gradient of a function in the presence of noise is central to several forms of reinforcement learning, including policy search methods. We present two te…

cs.LG2024

Evidence of Learned Look-Ahead in a Chess-Playing Neural Network

Erik Jenner, Shreyas Kapur, Vasil Georgiev +3

Do neural networks learn to implement algorithms such as look-ahead or search "in the wild"? Or do they rely purely on collections of simple heuristics? We present evidence of lear…

cs.AI2025

AssistanceZero: Scalably Solving Assistance Games

Cassidy Laidlaw, Eli Bronstein, Timothy Guo +5

Assistance games are a promising alternative to reinforcement learning from human feedback (RLHF) for training AI assistants. Assistance games resolve key drawbacks of RLHF, such a…

cs.LG2021

MADE: Exploration via Maximizing Deviation from Explored Regions

Tianjun Zhang, Paria Rashidinejad, Jiantao Jiao +3

In online reinforcement learning (RL), efficient exploration remains particularly challenging in high-dimensional environments with sparse rewards. In low-dimensional environments,…

cs.LG2012

A compact, hierarchical Q-function decomposition

Bhaskara Marthi, Stuart Russell, David Andre

Previous work in hierarchical reinforcement learning has faced a dilemma: either ignore the values of different possible exit states from a subroutine, thereby risking suboptimal b…

physics.geo-ph2023

Evidence for a kilometre-scale seismically slow layer atop the core-mantle boundary from normal modes

Stuart Russell, Jessica C. E. Irving, Lisanne Jagt +1

Geodynamic modelling and seismic studies have highlighted the possibility that a thin layer of low seismic velocities, potentially molten, may sit atop the core-mantle boundary but…

cs.MA2021

Accumulating Risk Capital Through Investing in Cooperation

Charlotte Roman, Michael Dennis, Andrew Critch +1

Recent work on promoting cooperation in multi-agent learning has resulted in many methods which successfully promote cooperation at the cost of becoming more vulnerable to exploita…

cs.LG2018

Learning and Planning with a Semantic Model

Yi Wu, Yuxin Wu, Aviv Tamar +3

Building deep reinforcement learning agents that can generalize and adapt to unseen environments remains a fundamental challenge for AI. This paper describes progresses on this cha…

cs.LG2025

Extractive Structures Learned in Pretraining Enable Generalization on Finetuned Facts

Jiahai Feng, Stuart Russell, Jacob Steinhardt

Pretrained language models (LMs) can generalize to implications of facts that they are finetuned on. For example, if finetuned on ``John Doe lives in Tokyo," LMs can correctly answ…

cs.CV2019

Bayesian Relational Memory for Semantic Visual Navigation

Yi Wu, Yuxin Wu, Aviv Tamar +3

We introduce a new memory architecture, Bayesian Relational Memory (BRM), to improve the generalization ability for semantic visual navigation agents in unseen environments, where…

cs.LG2020

SLIP: Learning to Predict in Unknown Dynamical Systems with Long-Term Memory

Paria Rashidinejad, Jiantao Jiao, Stuart Russell

We present an efficient and practical (polynomial time) algorithm for online prediction in unknown and partially observed linear dynamical systems (LDS) under stochastic noise. Whe…

cs.LG2025

BAMDP Shaping: a Unified Framework for Intrinsic Motivation and Reward Shaping

Aly Lidayan, Michael Dennis, Stuart Russell

Intrinsic motivation and reward shaping guide reinforcement learning (RL) agents by adding pseudo-rewards, which can lead to useful emergent behaviors. However, they can also encou…

cs.CL2025

How Do LLMs Perform Two-Hop Reasoning in Context?

Tianyu Guo, Hanlin Zhu, Ruiqi Zhang +4

``Socrates is human. All humans are mortal. Therefore, Socrates is mortal.'' This form of argument illustrates a typical pattern of two-hop reasoning. Formally, two-hop reasoning r…

cs.AI2012

Improving Gradient Estimation by Incorporating Sensor Data

Gregory Lawrence, Stuart Russell

An efficient policy search algorithm should estimate the local gradient of the objective function, with respect to the policy parameters, from as few trials as possible. Whereas mo…

cs.GT2020

Multi-Principal Assistance Games: Definition and Collegial Mechanisms

Arnaud Fickinger, Simon Zhuang, Andrew Critch +2

We introduce the concept of a multi-principal assistance game (MPAG), and circumvent an obstacle in social choice theory, Gibbard's theorem, by using a sufficiently collegial prefe…

cs.AI2025

The Singapore Consensus on Global AI Safety Research Priorities

Yoshua Bengio, Tegan Maharaj, Luke Ong +84

Rapidly improving AI capabilities and autonomy hold significant promise of transformation, but are also driving vigorous debate on how to ensure that AI is safe, i.e., trustworthy,…

cs.LG2022

Optimal Conservative Offline RL with General Function Approximation via Augmented Lagrangian

Paria Rashidinejad, Hanlin Zhu, Kunhe Yang +2

Offline reinforcement learning (RL), which refers to decision-making from a previously-collected dataset of interactions, has received significant attention over the past years. Mu…

cs.LG2022

Estimating and Penalizing Induced Preference Shifts in Recommender Systems

Micah Carroll, Anca Dragan, Stuart Russell +1

The content that a recommender system (RS) shows to users influences them. Therefore, when choosing a recommender to deploy, one is implicitly also choosing to induce specific inte…

cs.LG2021

Explore and Control with Adversarial Surprise

Arnaud Fickinger, Natasha Jaques, Samyak Parajuli +5

Unsupervised reinforcement learning (RL) studies how to leverage environment statistics to learn useful behaviors without the cost of reward engineering. However, a central challen…

cs.AI2025

GSM-Agent: Understanding Agentic Reasoning Using Controllable Environments

Hanlin Zhu, Tianyu Guo, Song Mei +4

As LLMs are increasingly deployed as agents, agentic reasoning - the ability to combine tool use, especially search, and reasoning - becomes a critical skill. However, it is hard t…

cs.AI2018

An Efficient, Generalized Bellman Update For Cooperative Inverse Reinforcement Learning

Dhruv Malik, Malayandi Palaniappan, Jaime F. Fisac +3

Our goal is for AI systems to correctly identify and act according to their human user's objectives. Cooperative Inverse Reinforcement Learning (CIRL) formalizes this value alignme…

cs.CY2026

International AI Safety Report 2026

Yoshua Bengio, Stephen Clare, Carina Prunkl +89

The International AI Safety Report 2026 synthesises the current scientific evidence on the capabilities, emerging risks, and safety of general-purpose AI systems. The report series…

cs.AI2015

Probabilistic Model-Based Approach for Heart Beat Detection

Hugh Chen, Yusuf Erol, Eric Shen +1

Nowadays, hospitals are ubiquitous and integral to modern society. Patients flow in and out of a veritable whirlwind of paperwork, consultations, and potential inpatient admissions…

cs.AI2025

Observation Interference in Partially Observable Assistance Games

Scott Emmons, Caspar Oesterheld, Vincent Conitzer +1

We study partially observable assistance games (POAGs), a model of the human-AI value alignment problem which allows the human and the AI assistant to have partial observations. Mo…

cs.AI2012

Gibbs Sampling in Open-Universe Stochastic Languages

Nimar S. Arora, Rodrigo de Salvo Braz, Erik B. Sudderth +1

Languages for open-universe probabilistic models (OUPMs) can represent situations with an unknown number of objects and iden- tity uncertainty. While such cases arise in a wide ran…

cs.LG2025

Reasoning by Superposition: A Theoretical Perspective on Chain of Continuous Thought

Hanlin Zhu, Shibo Hao, Zhiting Hu +3

Large Language Models (LLMs) have demonstrated remarkable performance in many applications, including challenging reasoning problems via chain-of-thoughts (CoTs) techniques that ge…

cs.AI2018

Discrete-Continuous Mixtures in Probabilistic Programming: Generalized Semantics and Inference Algorithms

Yi Wu, Siddharth Srivastava, Nicholas Hay +2

Despite the recent successes of probabilistic programming languages (PPLs) in AI applications, PPLs offer only limited support for random variables whose distributions combine disc…

cs.LG2025

Forecasting Seismic Waveforms: A Deep Learning Approach for Einstein Telescope

Waleed Esmail, Alexander Kappes, Stuart Russell +1

We introduce \textit{SeismoGPT}, a transformer-based model for forecasting three-component seismic waveforms in the context of future gravitational wave detectors like the Einstein…

cs.AI2013

Stochastic Simulation Algorithms for Dynamic Probabilistic Networks

Keiji Kanazawa, Daphne Koller, Stuart Russell

Stochastic simulation algorithms such as likelihood weighting often give fast, accurate approximations to posterior probabilities in probabilistic networks, and are the methods of…

cs.GT2024

The Partially Observable Off-Switch Game

Andrew Garber, Rohan Subramani, Linus Luu +3

A wide variety of goals could cause an AI to disable its off switch because "you can't fetch the coffee if you're dead" (Russell 2019). Prior theoretical work on this shutdown prob…

cs.LG2021

The MineRL BASALT Competition on Learning from Human Feedback

Rohin Shah, Cody Wild, Steven H. Wang +10

The last decade has seen a significant increase of interest in deep learning research, with many public successes that have demonstrated its potential. As such, these systems are n…

cs.AI2021

Scalable Online Planning via Reinforcement Learning Fine-Tuning

Arnaud Fickinger, Hengyuan Hu, Brandon Amos +2

Lookahead search has been a critical component of recent AI successes, such as in the games of chess, go, and poker. However, the search methods used in these games, and in many ot…

cs.NE2022

Pruned Neural Networks are Surprisingly Modular

Daniel Filan, Shlomi Hod, Cody Wild +2

The learned weights of a neural network are often considered devoid of scrutable internal structure. To discern structure in these weights, we introduce a measurable notion of modu…

cs.CY2025

International AI Safety Report

Yoshua Bengio, Sören Mindermann, Daniel Privitera +93

The first International AI Safety Report comprehensively synthesizes the current evidence on the capabilities, risks, and safety of advanced AI systems. The report was mandated by…

cs.LG2023

Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game

Sam Toyer, Olivia Watkins, Ethan Adrian Mendes +9

While Large Language Models (LLMs) are increasingly being used in real-world applications, they remain vulnerable to prompt injection attacks: malicious third party prompts that su…

cs.AI2024

Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems

David "davidad" Dalrymple, Joar Skalse, Yoshua Bengio +14

Ensuring that AI systems reliably and robustly avoid harmful or dangerous behaviours is a crucial challenge, especially for AI systems with a high degree of autonomy and general in…

cs.LG2024

Towards a Theoretical Understanding of the 'Reversal Curse' via Training Dynamics

Hanlin Zhu, Baihe Huang, Shaolun Zhang +4

Auto-regressive large language models (LLMs) show impressive capacities to solve many complex reasoning tasks while struggling with some simple logical reasoning tasks such as inve…

cs.CL2026

DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning

Hengyu Fu, Tianyu Guo, Zixuan Wang +5

Large language models achieve strong performance on many reasoning tasks when allowed to externalize intermediate steps as Chain-of-Thought (CoT). However, many questions require t…

cs.LG2022

imitation: Clean Imitation Learning Implementations

Adam Gleave, Mohammad Taufeeque, Juan Rocamonde +7

imitation provides open-source implementations of imitation and reward learning algorithms in PyTorch. We include three inverse reinforcement learning (IRL) algorithms, three imita…

cs.LG2021

Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design

Michael Dennis, Natasha Jaques, Eugene Vinitsky +4

A wide range of reinforcement learning (RL) problems - including robustness, transfer learning, unsupervised RL, and emergent complexity - require specifying a distribution of task…

cs.AI2024

AI Alignment with Changing and Influenceable Reward Functions

Micah Carroll, Davis Foote, Anand Siththaranjan +2

Existing AI alignment approaches assume that preferences are static, which is unrealistic: our preferences change, and may even be influenced by our interactions with AI systems th…

cs.LG2022

An Empirical Investigation of Representation Learning for Imitation

Xin Chen, Sam Toyer, Cody Wild +9

Imitation learning often needs a large demonstration set in order to handle the full range of situations that an agent might find itself in during deployment. However, collecting e…

cs.LG2026

When Do Autoregressive Sequence Models Forecast Physical Wavefields? A Controlled Study on Synthetic Seismograms

Waleed Esmail, Stuart Russell, Jana Klinge +2

Long-horizon autoregressive forecasting of oscillatory physical signals, such as seismograms, gravitational-wave strain, and similar wavefields is limited by error accumulation: as…

physics.geo-ph2022

A Re-examination of Ellipticity Corrections for Seismic Phases

Stuart Russell, John F. Rudge, Jessica C. E. Irving +1

The Earth's ellipticity of figure has an effect on the travel times of seismic waves over teleseismic distances. Tables of ellipticity corrections and coefficients have been used b…

stat.ML2021

Uncertain Decisions Facilitate Better Preference Learning

Cassidy Laidlaw, Stuart Russell

Existing observational approaches for learning human preferences, such as inverse reinforcement learning, usually make strong assumptions about the observability of the human's env…

cs.AI2014

Selecting Computations: Theory and Applications

Nicholas Hay, Stuart Russell, David Tolpin +1

Sequential decision problems are often approximately solvable by simulating possible future action sequences. Metalevel decision procedures have been developed for selecting which…

cs.LG2020

The MAGICAL Benchmark for Robust Imitation

Sam Toyer, Rohin Shah, Andrew Critch +1

Imitation Learning (IL) algorithms are typically evaluated in the same environment that was used to create demonstrations. This rewards precise reproduction of demonstrations in on…

cs.AI2016

Research Priorities for Robust and Beneficial Artificial Intelligence

Stuart Russell, Daniel Dewey, Max Tegmark

Success in the quest for artificial intelligence has the potential to bring unprecedented benefits to humanity, and it is therefore worthwhile to investigate how to maximize these…

cs.LG2013

Variational MCMC

Nando de Freitas, Pedro Hojen-Sorensen, Michael I. Jordan +1

We propose a new class of learning algorithms that combines variational approximation and Markov chain Monte Carlo (MCMC) simulation. Naive algorithms that use the variational appr…

cs.CY2025

International Scientific Report on the Safety of Advanced AI (Interim Report)

Yoshua Bengio, Sören Mindermann, Daniel Privitera +41

This is the interim publication of the first International Scientific Report on the Safety of Advanced AI. The report synthesises the scientific understanding of general-purpose AI…

cs.LG2025

Safe Learning Under Irreversible Dynamics via Asking for Help

Benjamin Plaut, Juan Liévano-Karim, Hanlin Zhu +1

Most learning algorithms with formal regret guarantees essentially rely on trying all possible behaviors, which is problematic when some errors cannot be recovered from. Instead, w…

cs.AI2017

Should Robots be Obedient?

Smitha Milli, Dylan Hadfield-Menell, Anca Dragan +1

Intuitively, obedience -- following the order that a human gives -- seems like a good property for a robot to have. But, we humans are not perfect and we may give orders that are n…