Reinforcement Learning
TowardtheFundamentalLimitsofImitation Learning
We then propose a novel algorithm based on minimum-distance functionals in the setting where the transition model is given and the expert is deterministic.Thealgorithmissuboptimalby .|S|H3/2/N,matchingourlower
Overleaf Example
We model episode sessions--parts of the episode where the latent state isfixed--and propose three keymodifications toexisting meta-RL methods: (i) consistency of latent information within sessions, (ii) session masking, and (iii) priorlatent conditioning.
Regularized Conditional Diffusion Model for Multi-Task Preference Alignment
Preferences serve as an alternative but recent work rarely considers preference learning given multiple tasks.
Safety through feedback in Constrained RL
This feedback can be system generated or elicited from a human observing the training process. Previous approaches have not been able to scale to complex environments and are constrained to receiving feedback at the state level which can be expensive to collect. To this end, we introduce an approach that scales to more complex domains and extends beyond state-level feedback, thus, reducing the burden on the evaluator.
