Evolving rewards to automate reinforcement learning

A Faust, A Francis, D Mehta - arXiv preprint arXiv:1905.07628, 2019 - arxiv.org
Many continuous control tasks have easily formulated objectives, yet using them directly as
a reward in reinforcement learning (RL) leads to suboptimal policies. Therefore, many …
被引用次数：59 相关文章

Evolving Rewards to Automate Reinforcement Learning

A Faust, A Francis, D Mehta - research.google
Many continuous control tasks have easily formulated objectives, yet using them directly as
a reward in reinforcement learning (RL) leads to suboptimal policies. Therefore, many …

Evolving Rewards to Automate Reinforcement Learning

A Faust, A Francis, D Mehta - arXiv e-prints, 2019 - ui.adsabs.harvard.edu
Many continuous control tasks have easily formulated objectives, yet using them directly as
a reward in reinforcement learning (RL) leads to suboptimal policies. Therefore, many …
[PDF] academia.edu

[PDF][PDF] Evolving Rewards to Automate Reinforcement Learning

A Faust, A Francis, D Mehta - arXiv preprint arXiv:1905.07628, 2019 - academia.edu
Many continuous control tasks have easily formulated objectives, yet using them directly as
a reward in reinforcement learning (RL) leads to suboptimal policies. Therefore, many …

Evolving Rewards to Automate Reinforcement Learning

A Faust, A Francis, D Mehta - research.google
Many continuous control tasks have easily formulated objectives, yet using them directly as
a reward in reinforcement learning (RL) leads to suboptimal policies. Therefore, many …