Intention-Conditioned Flow Occupancy Models
Paper • 2506.08902 • Published
Seohong Park
seohongpark
·
AI & ML interests
Reinforcement learning
Recent Activity
authored a paper about 8 hours ago
Intention-Conditioned Flow Occupancy Models authored a paper about 8 hours ago
Scalable Offline Model-Based RL with Action Chunks authored a paper about 8 hours ago
Unsupervised Skill Discovery with Bottleneck Option LearningOrganizations
authored 12
papers about 8 hours ago
Scalable Offline Model-Based RL with Action Chunks
Paper • 2512.08108 • Published
Unsupervised Skill Discovery with Bottleneck Option Learning
Paper • 2106.14305 • Published
Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods
Paper • 2111.03941 • Published
Lipschitz-constrained Unsupervised Skill Discovery
Paper • 2202.00914 • Published
HIQL: Offline Goal-Conditioned RL with Latent States as Actions
Paper • 2307.11949 • Published
Is Value Learning Really the Main Bottleneck in Offline RL?
Paper • 2406.09329 • Published
Unsupervised-to-Online Reinforcement Learning
Paper • 2408.14785 • Published
Flow Q-Learning
Paper • 2502.02538 • Published
Horizon Reduction Makes RL Scalable
Paper • 2506.04168 • Published
Dual Goal Representations
Paper • 2510.06714 • Published
Transitive RL: Value Learning via Divide and Conquer
Paper • 2510.22512 • Published
authored 7
papers 1 day ago
OGBench: Benchmarking Offline Goal-Conditioned RL
Paper • 2410.20092 • Published
GHIL-Glue: Hierarchical Control with Filtered Subgoal Images
Paper • 2410.20018 • Published
Reversal Q-Learning
Paper • 2606.17551 • Published
Decoupled Q-Chunking
Paper • 2512.10926 • Published
Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings
Paper • 2402.17135 • Published
Steering Your Diffusion Policy with Latent Space Reinforcement Learning
Paper • 2506.15799 • Published
Diffusion Guidance Is a Controllable Policy Improvement Operator
Paper • 2505.23458 • Published
updated a
dataset 1 day ago