Adversarial motion priors make good substitutes for complex reward functions

A Escontrela, XB Peng, W Yu, T Zhang… - 2022 IEEE/RSJ …, 2022 - ieeexplore.ieee.org
Training a high-dimensional simulated agent with an under-specified reward function often
leads the agent to learn physically infeasible strategies that are ineffective when deployed in …
被引用次数：70 相关文章

Adversarial Motion Priors Make Good Substitutes for Complex Reward Functions

A Escontrela, A Iscen, J Peng, K Goldberg, P Abbeel… - research.google
Training high-dimensional simulated agents with under-specified reward functions often
leads to jerky and unnatural behaviors, which results in physically infeasible strategies that …

Adversarial Motion Priors Make Good Substitutes for Complex Reward Functions

A Escontrela, XB Peng, W Yu, T Zhang, A Iscen… - arXiv e …, 2022 - ui.adsabs.harvard.edu
Training a high-dimensional simulated agent with an under-specified reward function often
leads the agent to learn physically infeasible strategies that are ineffective when deployed in …

Adversarial Motion Priors Make Good Substitutes for Complex Reward Functions

A Escontrela, XB Peng, W Yu, T Zhang, A Iscen… - arXiv preprint arXiv …, 2022 - arxiv.org
Training a high-dimensional simulated agent with an under-specified reward function often
leads the agent to learn physically infeasible strategies that are ineffective when deployed in …

Adversarial Motion Priors Make Good Substitutes for Complex Reward Functions

A Escontrela, A Iscen, J Peng, K Goldberg, P Abbeel… - research.google
Training high-dimensional simulated agents with under-specified reward functions often
leads to jerky and unnatural behaviors, which results in physically infeasible strategies that …