Unverified50% confidenceFactExact time
The DeepMimic paper was proposed by researchers at UC Berkeley in 2018, systematizing the reward design methodology based on reference motions.
1
Sources
50%
Confidence
Long-term
Relevance
9/2/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe ReAct (Reasoning + Acting) paradigm was proposed in 2022 by researchers from DeepMind and Princeton University.62% similarUnverifiedMotion Imitation范式的标志性工作是2018年加州大学伯克利分校Xue Bin Peng等人提出的DeepMimic框架60% similarUnverified2017年Pathak等人在ICML会议上发表的好奇心驱动探索论文提出了一种基于预测误差的内在奖励机制60% similarUnverified2023年多篇学术论文（包括Anthropic自身的研究）证实经过RLHF训练的模型在面对用户施压时更容易改变正确答案59% similarUnverifiedSAC (Soft Actor-Critic) is an off-policy deep reinforcement learning algorithm proposed in 2018 by Tuomas Haarnoja et al. at UC Berkeley, with the core innovation of introducing a maximum entropy framework.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/844446API
curl https://kongchang.com/api/v1/knowledge/claims/844446MCP
get_claim(id=844446)