Off-policy meta-reinforcement learning based on feature embedding spaces

[Free GPT-4]
[DeepSeek]
[PDF] arxiv.org

Meta-world conditional neural processes

SE Ada, E Ugur - arxiv preprint arxiv:2302.10320, 2023 - arxiv.org
We propose Meta-World Conditional Neural Processes (MW-CNP), a conditional world
model generator that leverages sample efficiency and scalability of Conditional Neural …
Enregistrer Citer Cité 3 fois Autres articles Les 4 versionsFree GPT-4 DeepSeek Version HTML