4 papers
Learning Dexterous Grasping from Sparse Taxonomy Guidance
Juhan Park, Taerim Yoon, Seungmin Kim +10
Dexterous manipulation requires planning a grasp configuration suited to the object and task, which is then executed through coordinated multi-finger control. However, specifying g…
TRACED: Transition-aware Regret Approximation with Co-learnability for Environment Design
Geonwoo Cho, Jaegyun Im, Jihwan Lee +3
Generalizing deep reinforcement learning agents to unseen environments remains a significant challenge. One promising solution is Unsupervised Environment Design (UED), a co-evolut…
AMPED: Adaptive Multi-objective Projection for balancing Exploration and skill Diversification
Geonwoo Cho, Jaemoon Lee, Jaegyun Im +3
Skill-based reinforcement learning (SBRL) enables rapid adaptation in environments with sparse rewards by pretraining a skill-conditioned policy. Effective skill learning requires…
Causal-Paced Deep Reinforcement Learning
Geonwoo Cho, Jaegyun Im, Doyoon Kim +1
Designing effective task sequences is crucial for curriculum reinforcement learning (CRL), where agents must gradually acquire skills by training on intermediate tasks. A key chall…