Picture for John Langford

John Langford

Towards Principled Representation Learning from Videos for Reinforcement Learning

Add code
Mar 20, 2024
Figure 1 for Towards Principled Representation Learning from Videos for Reinforcement Learning
Figure 2 for Towards Principled Representation Learning from Videos for Reinforcement Learning
Figure 3 for Towards Principled Representation Learning from Videos for Reinforcement Learning
Figure 4 for Towards Principled Representation Learning from Videos for Reinforcement Learning
Viaarxiv icon

Position Paper: Agent AI Towards a Holistic Intelligence

Feb 28, 2024
Viaarxiv icon

Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss

Add code
Feb 13, 2024
Viaarxiv icon

PcLast: Discovering Plannable Continuous Latent States

Add code
Nov 06, 2023
Viaarxiv icon

Streaming Active Learning with Deep Neural Networks

Add code
Mar 05, 2023
Figure 1 for Streaming Active Learning with Deep Neural Networks
Figure 2 for Streaming Active Learning with Deep Neural Networks
Figure 3 for Streaming Active Learning with Deep Neural Networks
Figure 4 for Streaming Active Learning with Deep Neural Networks
Viaarxiv icon

Towards Data-Driven Offline Simulations for Online Reinforcement Learning

Add code
Nov 14, 2022
Figure 1 for Towards Data-Driven Offline Simulations for Online Reinforcement Learning
Figure 2 for Towards Data-Driven Offline Simulations for Online Reinforcement Learning
Figure 3 for Towards Data-Driven Offline Simulations for Online Reinforcement Learning
Figure 4 for Towards Data-Driven Offline Simulations for Online Reinforcement Learning
Viaarxiv icon

Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information

Add code
Oct 31, 2022
Figure 1 for Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information
Figure 2 for Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information
Figure 3 for Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information
Figure 4 for Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information
Viaarxiv icon

Eigen Memory Trees

Add code
Oct 31, 2022
Figure 1 for Eigen Memory Trees
Figure 2 for Eigen Memory Trees
Figure 3 for Eigen Memory Trees
Figure 4 for Eigen Memory Trees
Viaarxiv icon

Guaranteed Discovery of Controllable Latent States with Multi-Step Inverse Models

Add code
Jul 17, 2022
Figure 1 for Guaranteed Discovery of Controllable Latent States with Multi-Step Inverse Models
Figure 2 for Guaranteed Discovery of Controllable Latent States with Multi-Step Inverse Models
Figure 3 for Guaranteed Discovery of Controllable Latent States with Multi-Step Inverse Models
Figure 4 for Guaranteed Discovery of Controllable Latent States with Multi-Step Inverse Models
Viaarxiv icon

Contextual Bandits with Large Action Spaces: Made Practical

Add code
Jul 12, 2022
Figure 1 for Contextual Bandits with Large Action Spaces: Made Practical
Figure 2 for Contextual Bandits with Large Action Spaces: Made Practical
Figure 3 for Contextual Bandits with Large Action Spaces: Made Practical
Figure 4 for Contextual Bandits with Large Action Spaces: Made Practical
Viaarxiv icon