Search Results for author:
Found 9 papers, 4 papers with code
Causal Analysis of Agent Behavior for AI Safety
As machine learning systems become more powerful they also become increasingly unpredictable and opaque.
Algorithms for Causal Reasoning in Probability Trees
Probability trees are one of the simplest models of causal generative processes.
Meta-trained agents implement Bayes-optimal agents
Memory-based meta-learning is a powerful technique to build agents that adapt fast to any task within a target distribution.
Avoiding Side Effects By Considering Future Tasks
To avoid this interference incentive, we introduce a baseline policy that represents a default course of action (such as doing nothing), and use it to filter out future tasks that are not achievable by default.
Scaling shared model governance via model splitting
Currently the only techniques for sharing governance of a deep learning model are homomorphic encryption and secure multiparty computation.
Scalable agent alignment via reward modeling: a research direction
One obstacle to applying reinforcement learning algorithms to real-world problems is the lack of suitable reward functions.
Penalizing side effects using stepwise relative reachability
How can we design safe reinforcement learning agents that avoid unnecessary disruptions to their environment?
AI Safety Gridworlds
We present a suite of reinforcement learning environments illustrating various safety properties of intelligent agents.
Deep reinforcement learning from human preferences
For sophisticated reinforcement learning (RL) systems to interact usefully with real-world environments, we need to communicate complex goals to these systems.
