Andrea Dittadi

The Role of Pretrained Representations for the OOD Generalization of Reinforcement Learning Agents

2021 · arXiv (Cornell University)

Building sample-efficient agents that generalize out-of-distribution (OOD) in real-world settings remains a fundamental unsolved problem on the path towards achieving higher-level cognition. One particularly promising approach is to begin with low-dimensional, pretrained representations of our …

DCI-ES: An Extended Disentanglement Framework with Connections to Identifiability

2022 · arXiv (Cornell University)

In representation learning, a common approach is to seek representations which disentangle the underlying factors of variation. Eastwood & Williams (2018) proposed three metrics for quantifying the quality of such disentangled representations: disentanglement (D), completeness …