Search Results for author:
Found 6 papers, 1 papers with code
Open Problems in Mechanistic Interpretability
Mechanistic interpretability aims to understand the computational mechanisms underlying neural networks' capabilities in order to accomplish concrete scientific and engineering goals.
Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero
Artificial Intelligence (AI) systems have made remarkable progress, attaining super-human performance across various domains.
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.
Meta-learning of Sequential Strategies
In this report we review memory-based meta-learning as a tool for building sample-efficient strategies that learn from past experience to adapt to any task within a target class.
