Log inSign up
Tianying Ji profile banner
user avatar

Tianying Ji

@jtinyng1
Ph.D. student at Tsinghua University. Interested in Reinforcement Learning & Robotics!
Beijing, China
jity16.github.io
Joined August 2022
39
Following
131
Followers
RepliesMedia
  • Pinned
    user avatar
    Tianying Ji
    @jtinyng1
    May 14, 2024
    🚀 Excited to share our latest research accepted by #ICML2024. Our paper “ACE: Off-Policy Actor-Critic with Causality-Aware Entropy Regularization” dives into leveraging primitive behaviors to enhance policy learning, and unveils the value of causal modeling in RL applications.🌟
    user avatar
    Yongyuan Liang
    @cheryyun_l
    May 14, 2024
    🐈‍⬛ Ever wonder how much different primitive behaviors impact policy learning? Introducing our #ICML2024 paper, "ACE: Off-Policy Actor-Critic with Causality-Aware Entropy Regularization", — boosting SAC by over 2x with only 41 extra training minutes! 🔗👇🏻: ace-rl.github.io
    Image
  • user avatar
    Tianying Ji
    @jtinyng1
    Jul 19, 2024
    Our #ICML2024 Oral paper ACE will be presented! Join us at Oral 3F Causality, Lehar 1-4, July 24th 11:15-11:30 CEST. Our poster session at Hall C 4-9 #1212, July 24th 11:30-13:00 CEST. Dive into the future of efficient RL and causality with us. See you there! ✨
    user avatar
    Yongyuan Liang
    @cheryyun_l
    Jul 19, 2024
    Our #ICML2024 Oral💐 paper ACE will be presented at Oral 3F Causality, Lehar 1-4, July 24th 11:15 a.m. - 11:30 a.m. CEST. And our poster session is at Hall C 4-9 #1212, July 24th 11:30 a.m. - 1:00 p.m. CEST. If you have interests in efficient RL and causality, check it out🥳!
    Image
  • user avatar
    Tianying Ji
    @jtinyng1
    Jun 2, 2024
    🎉 Excited to share that ACE has been selected for an oral presentation at #ICML2024! See you in Vienna! 😍🚀 #ICML #Vienna
    user avatar
    Tianying Ji
    @jtinyng1
    May 14, 2024
    🚀 Excited to share our latest research accepted by #ICML2024. Our paper “ACE: Off-Policy Actor-Critic with Causality-Aware Entropy Regularization” dives into leveraging primitive behaviors to enhance policy learning, and unveils the value of causal modeling in RL applications.🌟
  • user avatar
    Tianying Ji
    @jtinyng1
    May 14, 2024
    Five-year-old SAC and TD3 are still being used as the backbone algos today. Consider trying a new well-performing backbone without too much pain? Introducing our #ICML2024 paper, “Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic”!
    Image
    GIF
  • user avatar
    Tianying Ji
    @jtinyng1
    Jun 12, 2023
    Five-year-old algorithms SAC and TD3 are still being used as the backbone RL algos today. Consider trying a new well-performing backbone without too much pain? We introduce BAC, a simple but effective method that has a significant performance boost on various tasks. 🧵👇
    Image
    00:00