A tutorial on RLHF
SCALAR/MIDI Lab March, 2024;
slides

TLDR: A tutorial on DPO/cDPO/IPO/RSO.

RLRG presentation on Multi-Agent Diagnostics for Robustness via Illuminated Diversity
RLRG Feb 16, 2024;
slides

TLDR: How to use diversity search methods to obtain adversarial jailbreaks to policy?

RLRG presentation on Bridging Reinforcement Learning Theory and Practice with the Effective Horizon
RLRG September 1, 2023;
slides

TLDR: Bridging RL Theory and Practice.

RLRG presentation on Extreme Q-Learning
RLRG Feb 22, 2023;
slides

TLDR: A novel framework for Q-learning that models the maximal soft-values without needing to sample from a policy.

Research Preparation Exam at UT Austin
Research Preparation Exam April 25, 2023;
slides

rank-game: A unifying theory for learning from preferences and demonstrations.

RLRG presentation on The Information Geometry of Unsupervised Reinforcement Learning
RLRG September 21, 2022;
slides

TLDR: A explanation for the mutual information representation learning in RL.

Discussion on utility of parallel and differentiable simulators
SCALAR Lab;
slides

TLDR: How can parallel and differentiable simulators speed up reinforcement learning?