Learning Graphical Models
Causal Imitation for Markov Decision Processes: a Partial Identification Approach
Children often learn how to behave in an unfamiliar environment by imitating adults. Imitation learning (IL) enables a learning agent to behave in an unknown environment by observing expert demonstrations.
ACTOR S
We also demonstrate its effectiveness in generating robotic tasks.
IWBVT: Instance Weighting-based Bias-Variance Trade-off for Crowdsourcing
In recent years, a large number of algorithms for label integration and noise correction have been proposed to infer the unknown true labels of instances in crowdsourcing.
Deep Learning for Computing Convergence Rates of Markov Chains
Markovian models, estimating the rate of convergence to equilibrium is critical.
Leveraging an ECG Beat Diffusion Model for Morphological Reconstruction from Indirect Signals
Electrocardiogram (ECG) signals provide essential information about the heart's
Trajectory Data Suffices for Statistically Efficient Learning in Offline RL with Linear q-pi Realizability and Concentrability
The hope in this setting is that learning a good policy will be possible without requiring a sample size that scales with the number of states in the MDP . Foster et al. [ 2021 ] have shown this to be impossible even under concentrability, a data coverage assumption where a coefficient C
RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation
We introduce the first sample-efficient algorithm for LMDPs without any additional distributional assumptions . Our result builds off a new perspective on the role of off-policy evaluation guarantees and coverage coefficients in LMDPs, a perspective, that has been overlooked in the context of exploration in partially observed environments.
3D Gaussian Splatting as Markov Chain Monte Carlo
To do so, we revise the'cloning' of Gaussians
Axioms for AI Alignment from Human Feedback
In the context of reinforcement learning from human feedback (RLHF), the reward function is generally derived from maximum likelihood estimation of a random utility model based on pairwise comparisons made by humans. The problem of learning a reward function is one of preference aggregation that, we argue, largely falls within the scope of social choice theory. From this perspective, we can evaluate different aggregation methods via established axioms, examining whether these methods meet or fail well-known standards. We demonstrate that both the Bradley-Terry-Luce Model and its broad generalizations fail to meet basic axioms. In response, we develop novel rules for learning reward functions with strong axiomatic guarantees. A key innovation from the standpoint of social choice is that our problem has a linear structure, which greatly restricts the space of feasible rules and leads to a new paradigm that we call linear social choice .
