Creating Interactive Agents with Imitation Learning

On the Expressivity of Markov Reward

Unsupervised deep learning identifies semantic disentanglement in single inferotemporal face patch neurons

Is Curiosity All You Need? On the Utility of Emergent Behaviours from Curious Exploration

Challenges in Detoxifying Language Models

Enabling high-accuracy protein structure prediction at the proteome scale

Melting Pot: an evaluation suite for multi-agent reinforcement learning

Alchemy: A structured task distribution for meta-reinforcement learning

Data, Architecture, or Losses: What Contributes Most to Multimodal Transformer Success?

Imitating Interactive Intelligence

Using Unity to Help Solve Intelligence

RL Unplugged: Benchmarks for Offline Reinforcement Learning

dm_control: Software and Tasks for Continuous Control

Acme: A new framework for distributed reinforcement learning

Simple Sensor Intentions for Exploration

Learning to Segment Actions from Observation and Narration

Visual Grounding in Video for Unsupervised Word Translation

Artificial Intelligence, Values and Alignment

International evaluation of an AI system for breast cancer screening

Making Efficient Use of Demonstrations to Solve Hard Exploration Problems