DreamingV2: Reinforcement Learning with Discrete World Models without Reconstruction
Masashi Okada,Tadahiro Taniguchi,Masashi Okada,Tadahiro Taniguchi
The present paper proposes a novel reinforce-ment learning method with world models, DreamingV2, a collaborative extension of DreamerV2 and Dreaming. Dream- erV2 is a cutting-edge model-based reinforcement learning from pixels that uses discrete world models to represent latent states with categorical variables. Dreaming is also a form of reinforcement learning from pixels that attempts to avoid t...
