Good news: QDHF will be presented as a Spotlight at the NeurIPS 2023 ALOE workshop: sites.google.com/view/aloe2023. See you in New Orleans and let's chat!

Great work led by Ryan Bahlous-Boldi ! QD maintains diversity with pre-defined diversity metrics (or learned, e.g., QDHF!), but is it necessary? This paper proposes an alternative that uses MMO to solve deceptive RL tasks, and outperforms ME on QD-score w/o even optimizing towards it!

Thrilled to announce the first annual Reinforcement Learning Conference RL_Conference, which will be held at UMass Amherst August 9-12! RLC is the first strongly peer-reviewed RL venue with proceedings, and our call for papers is now available: rl-conference.cc. 🧵

Thrilled to announce the first annual Reinforcement Learning Conference RL_Conference, which will be held at UMass Amherst August 9-12! RLC is the first strongly peer-reviewed RL venue with proceedings, and our call for papers is now available: rl-conference.cc.

Had a great time yesterday presenting our QDHF work at #NeurIPS2023 ALOE Workshop! Fantastic workshop with great vibes. Glad to meet so many people in open-endedness, QD, RL, especially my amazing collaborators Jenny Zhang and Jeff Clune! (Thanks to Ryan Bahlous-Boldi for this photo!)

🚀Thrilled to release the QDHF tutorial in pyribs! Big shoutout to Bryon Tjanaka for his meticulous editing and insightful feedback👏. Dive into the tutorial to explore how QDHF enhances GenAI models with diversified, high-quality responses and apply these insights to your projects!

Preferences in RLHF often come from many people with differing values. Ryan's work explores how to infer a set of representative reward functions that captures that diversity, so that we can better reason about risk and fairness in these settings.

POPL enhances the safety and fairness of RLHF by aligning agents and LLMs with diverse human values. It effectively addresses hidden contexts in preferences, ensuring risk-sensitive alignment without additional labeling. Led by Ryan Bahlous-Boldi, w/ Lee Spector and Scott Niekum.

Thrilled to announce I’ve successfully defended my PhD! 🎓 Deeply grateful to my advisor Lee Spector, my committee Scott Niekum, Subhransu Maji, Jeff Clune, and all collaborators, friends, and family. Milestone achieved, excited for the next chapter!