Seohong Park

Publication Activity (10 Years)

Years Active: 2018-2024
Publications (10 Years): 19

Top Topics

Perceptual Aliasing

Policy Gradient

Reinforcement Learning

Top Venues

Publications

Seohong Park, Tobias Kreiman, Sergey Levine
Foundation Policies with Hilbert Representations. CoRR (2024)
Kevin Frans, Seohong Park, Pieter Abbeel, Sergey Levine
Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings. CoRR (2024)
Seohong Park, Kevin Frans, Sergey Levine, Aviral Kumar
Is Value Learning Really the Main Bottleneck in Offline RL? CoRR (2024)
Seohong Park, Oleh Rybkin, Sergey Levine
METRA: Scalable Unsupervised RL with Metric-Aware Abstraction. ICLR (2024)
Seohong Park, Dibya Ghosh, Benjamin Eysenbach, Sergey Levine
HIQL: Offline Goal-Conditioned RL with Latent States as Actions. CoRR (2023)
Seohong Park, Dibya Ghosh, Benjamin Eysenbach, Sergey Levine
HIQL: Offline Goal-Conditioned RL with Latent States as Actions. NeurIPS (2023)
Seohong Park, Kimin Lee, Youngwoon Lee, Pieter Abbeel
Controllability-Aware Unsupervised Skill Discovery. ICML (2023)
Seohong Park, Sergey Levine
Predictable MDP Abstraction for Unsupervised Model-Based RL. ICML (2023)
Seohong Park, Oleh Rybkin, Sergey Levine
METRA: Scalable Unsupervised RL with Metric-Aware Abstraction. CoRR (2023)
Seohong Park, Sergey Levine
Predictable MDP Abstraction for Unsupervised Model-Based RL. CoRR (2023)
Seohong Park, Kimin Lee, Youngwoon Lee, Pieter Abbeel
Controllability-Aware Unsupervised Skill Discovery. CoRR (2023)
Jaekyeom Kim, Seohong Park, Gunhee Kim
Constrained GPI for Zero-Shot Transfer in Reinforcement Learning. NeurIPS (2022)
Seohong Park, Jongwook Choi, Jaekyeom Kim, Honglak Lee, Gunhee Kim
Lipschitz-constrained Unsupervised Skill Discovery. ICLR (2022)
Seohong Park, Jongwook Choi, Jaekyeom Kim, Honglak Lee, Gunhee Kim
Lipschitz-constrained Unsupervised Skill Discovery. CoRR (2022)
Jaekyeom Kim, Seohong Park, Gunhee Kim
Unsupervised Skill Discovery with Bottleneck Option Learning. CoRR (2021)
Jaekyeom Kim, Seohong Park, Gunhee Kim
Unsupervised Skill Discovery with Bottleneck Option Learning. ICML (2021)
Seohong Park, Jaekyeom Kim, Gunhee Kim
Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods. CoRR (2021)
Seohong Park, Jaekyeom Kim, Gunhee Kim
Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods. NeurIPS (2021)
Younghyun Cho, Florian Negele, Seohong Park, Bernhard Egger, Thomas R. Gross
On-the-fly workload partitioning for integrated CPU/GPU architectures. PACT (2018)