↓Skip to main content

🏢 Singapore Management University

SPRINQL: Sub-optimal Demonstrations driven Offline Imitation Learning
·3010 words·15 mins· loading · loading
Machine Learning Reinforcement Learning 🏢 Singapore Management University
SPRINQL: Sub-optimal Demonstrations for Offline Imitation Learning
SampDetox: Black-box Backdoor Defense via Perturbation-based Sample Detoxification
·2579 words·13 mins· loading · loading
Machine Learning Deep Learning 🏢 Singapore Management University
SampDetox uses diffusion models to purify poisoned machine learning samples by strategically adding noise to eliminate backdoors without compromising data integrity.
Safety through feedback in Constrained RL
·2526 words·12 mins· loading · loading
Machine Learning Reinforcement Learning 🏢 Singapore Management University
Reinforcement Learning from Safety Feedback (RLSF) efficiently infers cost functions from trajectory-level feedback, enabling safe policy learning in complex environments.
Mimicking To Dominate: Imitation Learning Strategies for Success in Multiagent Games
·1956 words·10 mins· loading · loading
AI Generated Machine Learning Reinforcement Learning 🏢 Singapore Management University
IMAX-PPO: A novel multi-agent RL algorithm leveraging imitation learning to predict opponent actions, achieving superior performance in complex games.
Learning De-Biased Representations for Remote-Sensing Imagery
·2326 words·11 mins· loading · loading
Computer Vision Object Detection 🏢 Singapore Management University
DebLoRA: A novel unsupervised learning approach debiases LoRA for remote sensing imagery, boosting minor class performance without sacrificing major class accuracy.
Inverse Factorized Soft Q-Learning for Cooperative Multi-agent Imitation Learning
·3040 words·15 mins· loading · loading
Machine Learning Reinforcement Learning 🏢 Singapore Management University
New multi-agent imitation learning algorithm (MIFQ) leverages inverse soft Q-learning and factorization for stable, efficient training, achieving state-of-the-art results on challenging benchmarks.
Improving Environment Novelty Quantification for Effective Unsupervised Environment Design
·2893 words·14 mins· loading · loading
Reinforcement Learning 🏢 Singapore Management University
Boosting AI generalization: CENIE framework quantifies environment novelty via state-action coverage, enhancing unsupervised environment design for robust generalization.