Picture for Haonan Yu

Haonan Yu

VONet: Unsupervised Video Object Learning With Parallel U-Net Attention and Object-wise Sequential VAE

Add code
Jan 20, 2024
Viaarxiv icon

Policy Expansion for Bridging Offline-to-Online Reinforcement Learning

Add code
Feb 02, 2023
Figure 1 for Policy Expansion for Bridging Offline-to-Online Reinforcement Learning
Figure 2 for Policy Expansion for Bridging Offline-to-Online Reinforcement Learning
Figure 3 for Policy Expansion for Bridging Offline-to-Online Reinforcement Learning
Figure 4 for Policy Expansion for Bridging Offline-to-Online Reinforcement Learning
Viaarxiv icon

Generative Planning for Temporally Coordinated Exploration in Reinforcement Learning

Add code
Feb 03, 2022
Figure 1 for Generative Planning for Temporally Coordinated Exploration in Reinforcement Learning
Figure 2 for Generative Planning for Temporally Coordinated Exploration in Reinforcement Learning
Figure 3 for Generative Planning for Temporally Coordinated Exploration in Reinforcement Learning
Figure 4 for Generative Planning for Temporally Coordinated Exploration in Reinforcement Learning
Viaarxiv icon

Do You Need the Entropy Reward (in Practice)?

Add code
Jan 28, 2022
Figure 1 for Do You Need the Entropy Reward (in Practice)?
Figure 2 for Do You Need the Entropy Reward (in Practice)?
Figure 3 for Do You Need the Entropy Reward (in Practice)?
Figure 4 for Do You Need the Entropy Reward (in Practice)?
Viaarxiv icon

Towards Safe Reinforcement Learning with a Safety Editor Policy

Add code
Jan 28, 2022
Figure 1 for Towards Safe Reinforcement Learning with a Safety Editor Policy
Figure 2 for Towards Safe Reinforcement Learning with a Safety Editor Policy
Figure 3 for Towards Safe Reinforcement Learning with a Safety Editor Policy
Figure 4 for Towards Safe Reinforcement Learning with a Safety Editor Policy
Viaarxiv icon

TASAC: Temporally Abstract Soft Actor-Critic for Continuous Control

Add code
Apr 13, 2021
Figure 1 for TASAC: Temporally Abstract Soft Actor-Critic for Continuous Control
Figure 2 for TASAC: Temporally Abstract Soft Actor-Critic for Continuous Control
Figure 3 for TASAC: Temporally Abstract Soft Actor-Critic for Continuous Control
Figure 4 for TASAC: Temporally Abstract Soft Actor-Critic for Continuous Control
Viaarxiv icon

MetaView: Few-shot Active Object Recognition

Add code
Mar 07, 2021
Figure 1 for MetaView: Few-shot Active Object Recognition
Figure 2 for MetaView: Few-shot Active Object Recognition
Figure 3 for MetaView: Few-shot Active Object Recognition
Figure 4 for MetaView: Few-shot Active Object Recognition
Viaarxiv icon

Hierarchical Reinforcement Learning By Discovering Intrinsic Options

Add code
Jan 16, 2021
Figure 1 for Hierarchical Reinforcement Learning By Discovering Intrinsic Options
Figure 2 for Hierarchical Reinforcement Learning By Discovering Intrinsic Options
Figure 3 for Hierarchical Reinforcement Learning By Discovering Intrinsic Options
Figure 4 for Hierarchical Reinforcement Learning By Discovering Intrinsic Options
Viaarxiv icon

Why Build an Assistant in Minecraft?

Add code
Jul 25, 2019
Viaarxiv icon

CraftAssist: A Framework for Dialogue-enabled Interactive Agents

Add code
Jul 19, 2019
Figure 1 for CraftAssist: A Framework for Dialogue-enabled Interactive Agents
Figure 2 for CraftAssist: A Framework for Dialogue-enabled Interactive Agents
Figure 3 for CraftAssist: A Framework for Dialogue-enabled Interactive Agents
Figure 4 for CraftAssist: A Framework for Dialogue-enabled Interactive Agents
Viaarxiv icon