Jayden
@jaydenteoh.bsky.social
Undergraduate researcher. Interested in generalization, multi-objective reinforcement learning, and open-endedness | Looking for PhD in RL in 2026
My works: https://scholar.google.com/citations?user=GnHpLE8AAAAJ&hl=en
My works: https://scholar.google.com/citations?user=GnHpLE8AAAAJ&hl=en
Been feeling FOMO from all the ICLR posts the past 2 days. Will finally be at the conference tomorrow. Please do come by our poster and I’m happy to chat! 😊
⏰: Sat, 26 Apr 3pm
📍: Hall 3 + Hall 2B Poster 374
⏰: Sat, 26 Apr 3pm
📍: Hall 3 + Hall 2B Poster 374
April 25, 2025 at 5:40 PM
Been feeling FOMO from all the ICLR posts the past 2 days. Will finally be at the conference tomorrow. Please do come by our poster and I’m happy to chat! 😊
⏰: Sat, 26 Apr 3pm
📍: Hall 3 + Hall 2B Poster 374
⏰: Sat, 26 Apr 3pm
📍: Hall 3 + Hall 2B Poster 374
Our baseline evaluations of current MORL algorithms uncover 2 key insights:
1) Current MORL algorithms struggle with generalization.
2) However, MORL demonstrate greater potential for learning adaptable behaviors for generalization compared to single-objective.
1) Current MORL algorithms struggle with generalization.
2) However, MORL demonstrate greater potential for learning adaptable behaviors for generalization compared to single-objective.
March 5, 2025 at 6:59 AM
Our baseline evaluations of current MORL algorithms uncover 2 key insights:
1) Current MORL algorithms struggle with generalization.
2) However, MORL demonstrate greater potential for learning adaptable behaviors for generalization compared to single-objective.
1) Current MORL algorithms struggle with generalization.
2) However, MORL demonstrate greater potential for learning adaptable behaviors for generalization compared to single-objective.
We also introduce a benchmark featuring diverse multi-objective domains with parameterized environment configurations to facilitate studies in this area.
March 5, 2025 at 6:59 AM
We also introduce a benchmark featuring diverse multi-objective domains with parameterized environment configurations to facilitate studies in this area.