World models enable efficient AI planning but create risks from adversarial corruption, goal misgeneralization, and human bias, demonstrated via attacks that amplify errors and reduce rewards on models like RSSM and DreamerV3.
MOReL: Model-based offline reinforcement learning
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
A comprehensive benchmark study of offline imitation learning methods on multi-stage robot manipulation tasks identifies key sensitivities to algorithm design, data quality, and stopping criteria while releasing all datasets and code.
Offline RL promises to extract high-utility policies from static datasets but faces fundamental challenges that current methods only partially address.
citing papers explorer
-
Safety, Security, and Cognitive Risks in World Models
World models enable efficient AI planning but create risks from adversarial corruption, goal misgeneralization, and human bias, demonstrated via attacks that amplify errors and reduce rewards on models like RSSM and DreamerV3.
-
What Matters in Learning from Offline Human Demonstrations for Robot Manipulation
A comprehensive benchmark study of offline imitation learning methods on multi-stage robot manipulation tasks identifies key sensitivities to algorithm design, data quality, and stopping criteria while releasing all datasets and code.
-
Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
Offline RL promises to extract high-utility policies from static datasets but faces fundamental challenges that current methods only partially address.
- Learning to Theorize the World from Observation