17 citations · 31 across the 13 of their papers we have counts for
15 papers
BooST: Bridging Semantics and Motions for Efficient Skill Transfer
Jusuk Lee, Daesol Cho, Jonghun Shin +4
Skill abstraction---the process of learning reusable and temporally extended behaviors---has emerged as a key paradigm for improving sample efficiency and generalization in robot l…
FLAG: Flow Policy MaxEnt-RL by Latent Augmented Guidance
Sungha Kim, Gawon Lee, Jusuk Lee +3
Maximum entropy reinforcement learning (MaxEnt-RL) enables robust exploration, yet practical implementations often restrict policies to simple Gaussians. While recent approaches in…
DynaFLIP: Rethinking Robotics Perception via Tri-Modal-Dynamics Guided Representation
Jusuk Lee, Seungjae Lee, Jonghun Shin +6
Robot manipulation critically depends on perception that preserves the action-relevant aspects of a scene. Yet most robot learning pipelines are built upon visual encoders pre-trai…
EgoAVFlow: Robot Policy Learning with Active Vision from Human Egocentric Videos via 3D Flow
Daesol Cho, Youngseok Jang, Danfei Xu +1
Egocentric human videos provide a scalable source of manipulation demonstrations; however, deploying them on robots requires active viewpoint control to maintain task-critical visi…
Temporal Action Representation Learning for Tactical Resource Control and Subsequent Maneuver Generation
Hoseong Jung, Sungil Son, Daesol Cho +3
Autonomous robotic systems should reason about resource control and its impact on subsequent maneuvers, especially when operating with limited energy budgets or restricted sensing.…
AdaptManip: Learning Adaptive Whole-Body Object Lifting and Delivery with Online Recurrent State Estimation
Morgan Byrd, Donghoon Baek, Kartik Garg +5
This paper presents Adaptive Whole-body Loco-Manipulation, AdaptManip, a fully autonomous framework for humanoid robots to perform integrated navigation, object lifting, and delive…
Periodic Skill Discovery
Jonghae Park, Daesol Cho, Jusuk Lee +3
Unsupervised skill discovery in reinforcement learning (RL) aims to learn diverse behaviors without relying on external rewards. However, current methods often overlook the periodi…
Leveraging Temporally Extended Behavior Sharing for Multi-task Reinforcement Learning
Gawon Lee, Daesol Cho, H. Jin Kim
Multi-task reinforcement learning (MTRL) offers a promising approach to improve sample efficiency and generalization by training agents across multiple tasks, enabling knowledge sh…
Diversify & Conquer: Outcome-directed Curriculum RL via Out-of-Distribution Disagreement
Daesol Cho, Seungjae Lee, H. Jin Kim
Reinforcement learning (RL) often faces the challenges of uninformed search problems where the agent should explore without access to the domain knowledge such as characteristics o…
CQM: Curriculum Reinforcement Learning with a Quantized World Model
Seungjae Lee, Daesol Cho, Jonghae Park +1
Recent curriculum Reinforcement Learning (RL) has shown notable progress in solving complex tasks by proposing sequences of surrogate tasks. However, the previous approaches often…
Demonstration-free Autonomous Reinforcement Learning via Implicit and Bidirectional Curriculum
Jigang Kim, Daesol Cho, H. Jin Kim
While reinforcement learning (RL) has achieved great success in acquiring complex skills solely from environmental interactions, it assumes that resets to the initial state are rea…
Outcome-directed Reinforcement Learning by Uncertainty & Temporal Distance-Aware Curriculum Goal Generation
Daesol Cho, Seungjae Lee, H. Jin Kim
Current reinforcement learning (RL) often suffers when solving a challenging exploration problem where the desired outcomes or high rewards are rarely observed. Even though curricu…
S2P: State-conditioned Image Synthesis for Data Augmentation in Offline Reinforcement Learning
Daesol Cho, Dongseok Shim, H. Jin Kim
Offline reinforcement learning (Offline RL) suffers from the innate distributional shift as it cannot interact with the physical environment during training. To alleviate such limi…
Unsupervised Reinforcement Learning for Transferable Manipulation Skill Discovery
Daesol Cho, Jigang Kim, H. Jin Kim
Current reinforcement learning (RL) in robotics often experiences difficulty in generalizing to new downstream tasks due to the innate task-specific training paradigm. To alleviate…
Automating Reinforcement Learning with Example-based Resets
Jigang Kim, J. hyeon Park, Daesol Cho +1
Deep reinforcement learning has enabled robots to learn motor skills from environmental interactions with minimal to no prior knowledge. However, existing reinforcement learning al…