Meta-Reward-Net: Implicitly Differentiable Reward Learning for Preference-based Reinforcement Learning
Download Abstract: Setting up a well-designed reward fu …
NeurIPS
A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learning
Download Abstract: Gradient-based Meta-RL (GMRL) refers …
A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learning 查看全文 »
A Unified Diversity Measure for Multiagent Reinforcement Learning
Download Abstract: Promoting behavioural diversity is o …
A Unified Diversity Measure for Multiagent Reinforcement Learning 查看全文 »
Efficient Meta Reinforcement Learning for Preference-based Fast Adaptation
Download Abstract: Learning new task-specific skills fr …
Efficient Meta Reinforcement Learning for Preference-based Fast Adaptation 查看全文 »
Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning
Download Abstract: Achieving human-level dexterity is a …
Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning 查看全文 »
On the Learning Mechanisms in Physical Reasoning
Download Abstract: Is dynamics prediction indispensable …
HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes
Download Abstract: Learning to generate diverse scene-a …
HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes 查看全文 »
EgoTaskQA: Understanding Human Tasks in Egocentric Videos
Download Abstract: Understanding human tasks through vi …
EgoTaskQA: Understanding Human Tasks in Egocentric Videos 查看全文 »
TarGF: Learning Target Gradient Field for Object Rearrangement
Download Abstract: Object Rearrangement is to move obje …
TarGF: Learning Target Gradient Field for Object Rearrangement 查看全文 »
MATE: Benchmarking Multi-Agent Reinforcement Learning in Distributed Target Coverage Control
Download Abstract: We introduce the Multi-Agent Trackin …
MATE: Benchmarking Multi-Agent Reinforcement Learning in Distributed Target Coverage Control 查看全文 »