Disentangled Skill Embeddings (DSE) is a variational inference framework for multi-task RL using shared parameters and task-specific latent embeddings for generalization to unseen conditions and as skills in hierarchical RL.
Transfer learning for reinforcement learning domains: A survey,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2019 2verdicts
UNVERDICTED 2representative citing papers
Introduces three strategic learning schemes for active cyber defenses under parameter, payoff, and environmental uncertainty that share a sensation-estimation-action feedback loop to converge on optimal policies.
citing papers explorer
-
Disentangled Skill Embeddings for Reinforcement Learning
Disentangled Skill Embeddings (DSE) is a variational inference framework for multi-task RL using shared parameters and task-specific latent embeddings for generalization to unseen conditions and as skills in hierarchical RL.
-
Strategic Learning for Active, Adaptive, and Autonomous Cyber Defense
Introduces three strategic learning schemes for active cyber defenses under parameter, payoff, and environmental uncertainty that share a sensation-estimation-action feedback loop to converge on optimal policies.