Paper
Publication
Alchemy: A structured task distribution for meta-reinforcement learning
Paper
Publication
Physically Embedded Planning Problems: New Challenges for Reinforcement Learning
Paper
Publication
Human Instruction-Following with Deep Reinforcement Learning via Transfer-Learning from Text
Paper
Publication
An empirical investigation of the challenges of real-world reinforcement learning
Paper
Publication
The MineRL Competition on Sample-Efficient Reinforcement Learning Using Human Priors: A Retrospective
Paper
Publication
Unsupervised Doodling and Painting with Improved SPIRAL
Paper
Publication
Making Efficient Use of Demonstrations to Solve Hard Exploration Problems
Paper
Publication
OpenSpiel: A Framework for Reinforcement Learning in Games
Paper
Publication
Behaviour Suite for Reinforcement Learning
Paper
Publication
Interval Timing in Deep Reinforcement Learning Agents
Paper
Publication
Human-level performance in 3D multiplayer games with population-based reinforcement learning
Paper
Publication
COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration
Paper
Publication
Meta reinforcement learning as task inference
Paper
Publication
Learned human-agent decision-making, communication and joint action in a virtual reality environment
Paper
Publication
Penalizing side effects using stepwise relative reachability
Paper
Publication
Autocurricula and the Emergence of Innovation from Social Interaction: A Manifesto for Multi-Agent Intelligence Research
Paper
Publication
The Hanabi Challenge: A New Frontier for AI Research
Paper
Publication
Learning to Navigate in Cities Without a Map
Paper
Publication
Malthusian Reinforcement Learning
Paper
Publication
Learning Latent Dynamics for Planning from Pixels
Paper
Publication
Episodic Curiosity through Reachability
Paper
Publication
Deep reinforcement learning with relational inductive biases
Paper
Publication
Learning Deployable Navigation Policies at Kilometer Scale from a Single Traversal
Paper
Publication
Measuring and avoiding side effects using relative reachability
Paper
Publication
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures