Zobrazeno 1 - 2
of 2
pro vyhledávání: '"George D. Konidaris"'
Autor:
Josh Roy, George D. Konidaris
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 35:9454-9462
We introduce Wasserstein Adversarial Proximal Policy Optimization (WAPPO), a novel algorithm for visual transfer in Reinforcement Learning that explicitly learns to align the distributions of extracted features between a source and target task. WAPPO
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3e2e24cf3092d7ec3a9a35d6e9f7b192
https://doi.org/10.1609/aaai.v35i11.17139
https://doi.org/10.1609/aaai.v35i11.17139
A core operation in reinforcement learning (RL) is finding an action that is optimal with respect to a learned value function. This operation is often challenging when the learned value function takes continuous actions as input. We introduce deep ra
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9534aa18dd8d0e584b9d19c9a741e335
