research
∙
07/28/2023
The Hydra Effect: Emergent Self-repair in Language Model Computations
We investigate the internal structure of language model computations usi...
share
research
∙
05/26/2023
Randomized Positional Encodings Boost Length Generalization of Transformers
Transformers have impressive generalization capabilities on tasks with a...
research
∙
09/30/2022
Beyond Bayes-optimality: meta-learning what you know you don't know
Meta-training agents with memory has been shown to culminate in Bayes-op...
research
∙
07/05/2022
Neural Networks and the Chomsky Hierarchy
Reliable generalization lies at the heart of safe ML and AI. However, un...
research
∙
03/23/2022
Your Policy Regularizer is Secretly an Adversary
Policy regularization methods such as maximum entropy regularization are...
research
∙
01/20/2022
Safe Deep RL in 3D Environments using Human Feedback
Agents should avoid unsafe behaviour during both training and deployment...
research
∙
11/04/2021
Model-Free Risk-Sensitive Reinforcement Learning
We extend temporal-difference (TD) learning in order to obtain risk-sens...
research
∙
10/20/2021
Shaking the foundations: delusions in sequence models for interaction and control
The recent phenomenal success of language models has reinvigorated machi...
research
∙
03/05/2021
Causal Analysis of Agent Behavior for AI Safety
As machine learning systems become more powerful they also become increa...
research
∙
02/02/2021
Agent Incentives: A Causal Perspective
We present a framework for analysing agent incentives using causal influ...
research
∙
11/17/2020
Avoiding Tampering Incentives in Deep RL via Decoupled Approval
How can we design agents that pursue a given objective when all feedback...
research
∙
11/17/2020
REALab: An Embedded Perspective on Tampering
This paper describes REALab, a platform for embedded agency research in ...
research
∙
10/23/2020
Algorithms for Causal Reasoning in Probability Trees
Probability trees are one of the simplest models of causal generative pr...
research
∙
10/21/2020
Meta-trained agents implement Bayes-optimal agents
Memory-based meta-learning is a powerful technique to build agents that ...
research
∙
10/15/2020
Avoiding Side Effects By Considering Future Tasks
Designing reward functions is difficult: the designer has to specify wha...
research
∙
06/24/2020
Quantifying Differences in Reward Functions
For many tasks, the reward function is too complex to be specified proce...
research
∙
04/28/2020
Pitfalls of learning a reward function online
In some agent designs like inverse reinforcement learning an agent needs...
research
∙
01/20/2020
The Incentives that Shape Behaviour
Which variables does an agent have an incentive to control with its deci...
research
∙
12/05/2019
Learning Human Objectives by Evaluating Hypothetical Behavior
We seek to align agent behavior with a user's objectives in a reinforcem...
research
∙
06/20/2019
Modeling AGI Safety Frameworks with Causal Influence Diagrams
Proposals for safe AGI systems are typically made at the level of framew...
research
∙
05/08/2019
Meta-learning of Sequential Strategies
In this report we review memory-based meta-learning as a tool for buildi...
research
∙
02/26/2019
Understanding Agent Incentives using Causal Influence Diagrams, Part I: Single Action Settings
Agents are systems that optimize an objective function in an environment...
research
∙
01/08/2019
Soft-Bayes: Prod for Mixtures of Experts with Log-Loss
We consider prediction with expert advice under the log-loss with the go...
research
∙
12/14/2018
Scaling shared model governance via model splitting
Currently the only techniques for sharing governance of a deep learning ...
research
∙
11/19/2018
Scalable agent alignment via reward modeling: a research direction
One obstacle to applying reinforcement learning algorithms to real-world...
research
∙
11/15/2018
Reward learning from human preferences and demonstrations in Atari
To solve complex real-world problems with reinforcement learning, we can...
research
∙
06/30/2018
Modeling Friends and Foes
How can one detect friendly and adversarial behavior from raw data? Dete...
research
∙
06/04/2018
Measuring and avoiding side effects using relative reachability
How can we design reinforcement learning agents that avoid causing unnec...
research
∙
05/31/2018
Agents and Devices: A Relative Definition of Agency
According to Dennett, the same system may be described using a `physical...
research
∙
02/05/2018
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
In this work we aim to solve a large collection of tasks using a single ...
research
∙
01/24/2018
Psychlab: A Psychology Laboratory for Deep Reinforcement Learning Agents
Psychlab is a simulated psychology laboratory inside the first-person 3D...
research
∙
11/27/2017
AI Safety Gridworlds
We present a suite of reinforcement learning environments illustrating v...
research
∙
11/14/2017
Symmetric Decomposition of Asymmetric Games
We introduce new theoretical insights into two-population asymmetric gam...
research
∙
06/30/2017
Noisy Networks for Exploration
We introduce NoisyNet, a deep reinforcement learning agent with parametr...
research
∙
06/12/2017
Deep reinforcement learning from human preferences
For sophisticated reinforcement learning (RL) systems to interact useful...
research
∙
05/23/2017
Reinforcement Learning with a Corrupted Reward Channel
No real-world reward function is perfect. Sensory errors and software bu...
research
∙
12/12/2016
DeepMind Lab
DeepMind Lab is a first-person 3D game platform designed for research an...
research
∙
07/15/2015
Massively Parallel Methods for Deep Reinforcement Learning
We present the first massively distributed architecture for deep reinfor...
research
∙
09/27/2011
An Approximation of the Universal Intelligence Measure
The Universal Intelligence Measure is a recently proposed formal definit...
research
∙
10/20/2006
Fitness Uniform Optimization
In evolutionary algorithms, the fitness of a population increases with t...
research
∙
04/11/2005