Seohong Park

ogbench. A benchmark for offline goal-conditioned RL and offline RL

fql. The official implementation of flow Q-learning (FQL)

horizon-reduction. The official implementation of "Horizon Reduction Makes RL Scalable"

HILP. Foundation Policies with Hilbert Representations (ICML 2024)

HIQL. HIQL: Offline Goal-Conditioned RL with Latent States as Actions (NeurIPS 2023)

METRA. METRA: Scalable Unsupervised RL with Metric-Aware Abstraction (ICLR 2024)

LSD. Lipschitz-constrained Unsupervised Skill Discovery (ICLR 2022)

PMA. Predictable MDP Abstraction for Unsupervised Model-Based RL (ICML 2023)

CSD-manipulation. Controllability-Aware Unsupervised Skill Discovery (ICML 2023)

CSD-locomotion. Controllability-Aware Unsupervised Skill Discovery (ICML 2023)

SAR. Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods (NeurIPS 2021)