12 papers
Generative Support Realignment for Cross-Domain Offline Reinforcement Learning
Minung Kim, Jeongmo Kim, Gwanwoo Choi +1
Cross-domain offline reinforcement learning learns a target policy from pre-collected source and target datasets with different dynamics. When target data are scarce, effectively c…
Shaping Zero-Shot Coordination via State Blocking
Mingu Kang, Sunwoo Lee, Yonghyeon Jo +1
Zero-shot coordination (ZSC) aims to enable agents to cooperate with independently trained partners without prior interaction, a key requirement for real-world multi-agent systems…
Flow Actor-Critic for Offline Reinforcement Learning
Jongseong Chae, Jongeui Park, Yongjae Shin +3
The dataset distributions in offline reinforcement learning (RL) often exhibit complex and multi-modal distributions, necessitating expressive policies to capture such distribution…
Retaining Suboptimal Actions to Follow Shifting Optima in Multi-Agent Reinforcement Learning
Yonghyeon Jo, Sunwoo Lee, Seungyul Han
Value decomposition is a core approach for cooperative multi-agent reinforcement learning (MARL). However, existing methods still rely on a single optimal action and struggle to ad…
Strict Subgoal Execution: Reliable Long-Horizon Planning in Hierarchical Reinforcement Learning
Jaebak Hwang, Sanghyeon Lee, Jeongmo Kim +1
Long-horizon goal-conditioned tasks pose fundamental challenges for reinforcement learning (RL), particularly when goals are distant and rewards are sparse. While hierarchical and…
Focusing Influence Mechanism for Multi-Agent Reinforcement Learning
Yisak Park, Sunwoo Lee, Seungyul Han
Cooperative multi-agent reinforcement learning (MARL) under sparse rewards remains fundamentally challenging because agents often fail to concentrate their influence, leading to in…
Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations
Minung Kim, Kawon Lee, Jungmo Kim +2
Imitation learning (IL) enables agents to mimic expert behavior without reward signals but faces challenges in cross-domain scenarios with high-dimensional, noisy, and incomplete v…
Self-Improving Skill Learning for Robust Skill-based Meta-Reinforcement Learning
Sanghyeon Lee, Sangjun Bae, Yisak Park +1
Meta-reinforcement learning (Meta-RL) facilitates rapid adaptation to unseen tasks but faces challenges in long-horizon environments. Skill-based approaches tackle this by decompos…
Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement Learning
Sunwoo Lee, Jaebak Hwang, Yonghyeon Jo +1
Traditional robust methods in multi-agent reinforcement learning (MARL) often struggle against coordinated adversarial attacks in cooperative scenarios. To address this limitation,…
Task-Aware Virtual Training: Enhancing Generalization in Meta-Reinforcement Learning for Out-of-Distribution Tasks
Jeongmo Kim, Yisak Park, Minung Kim +1
Meta reinforcement learning aims to develop policies that generalize to unseen tasks sampled from a task distribution. While context-based meta-RL methods improve task representati…
Exclusively Penalized Q-learning for Offline Reinforcement Learning
Junghyuk Yeom, Yonghyeon Jo, Jungmo Kim +2
Constraint-based offline reinforcement learning (RL) involves policy constraints or imposing penalties on the value function to mitigate overestimation errors caused by distributio…
CLIP-VQDiffusion : Langauge Free Training of Text To Image generation using CLIP and vector quantized diffusion model
Seungdae Han, Joohee Kim
There has been a significant progress in text conditional image generation models. Recent advancements in this field depend not only on improvements in model structures, but also v…