reinformed-dreamer-ec886933·1 events·first seen Aliases: Reinformed Dreamer
A new arXiv preprint introduces Reinformed Dreamer, a model-based reinforcement learning algorithm that extends the Informed Dreamer approach with a novel asymmetric representation learning objective using latent guidance. The authors identify a limitation in how Informed Dreamer learns privileged information representations and propose a fix that yields more consistent benchmark improvements. The work contributes to the asymmetric RL paradigm, which leverages additional state information during training beyond reward signals.