8 citations · 30 across the 23 of their papers we have counts for
24 papers
Decoupled Q-Chunking
Qiyang Li, Seohong Park, Sergey Levine
Temporal-difference (TD) methods learn state and action values efficiently by bootstrapping from their own future value predictions, but such a self-bootstrapping mechanism is pron…
Scalable Offline Model-Based RL with Action Chunks
Kwanyoung Park, Seohong Park, Youngwoon Lee +1
In this paper, we study whether model-based reinforcement learning (RL), in particular model-based value expansion, can provide a scalable recipe for tackling complex, long-horizon…
Transitive RL: Value Learning via Divide and Conquer
Seohong Park, Aditya Oberai, Pranav Atreya +1
In this work, we present Transitive Reinforcement Learning (TRL), a new value learning algorithm based on a divide-and-conquer paradigm. TRL is designed for offline goal-conditione…
Dual Goal Representations
Seohong Park, Deepinder Mann, Sergey Levine
In this work, we introduce dual goal representations for goal-conditioned reinforcement learning (GCRL). A dual goal representation characterizes a state by "the set of temporal di…
Steering Your Diffusion Policy with Latent Space Reinforcement Learning
Andrew Wagenmaker, Mitsuhiko Nakamoto, Yunchu Zhang +5
Robotic control policies learned from human demonstrations have achieved impressive results in many real-world applications. However, in scenarios where initial performance is not…
Intention-Conditioned Flow Occupancy Models
Chongyi Zheng, Seohong Park, Sergey Levine +1
Large-scale pre-training has fundamentally changed how machine learning research is done today: large foundation models are trained once, and then can be used by anyone in the comm…
Horizon Reduction Makes RL Scalable
Seohong Park, Kevin Frans, Deepinder Mann +3
In this work, we study the scalability of offline reinforcement learning (RL) algorithms. In principle, a truly scalable offline RL algorithm should be able to solve any given prob…
Diffusion Guidance Is a Controllable Policy Improvement Operator
Kevin Frans, Seohong Park, Pieter Abbeel +1
At the core of reinforcement learning is the idea of learning beyond the performance in the data. However, scaling such systems has proven notoriously tricky. In contrast, techniqu…
Flow Q-Learning
Seohong Park, Qiyang Li, Sergey Levine
We present flow Q-learning (FQL), a simple and performant offline reinforcement learning (RL) method that leverages an expressive flow-matching policy to model arbitrarily complex…
GHIL-Glue: Hierarchical Control with Filtered Subgoal Images
Kyle B. Hatch, Ashwin Balakrishna, Oier Mees +8
Image and video generative models that are pre-trained on Internet-scale data can greatly increase the generalization capacity of robot learning systems. These models can function…
OGBench: Benchmarking Offline Goal-Conditioned RL
Seohong Park, Kevin Frans, Benjamin Eysenbach +1
Offline goal-conditioned reinforcement learning (GCRL) is a major problem in reinforcement learning (RL) because it provides a simple, unsupervised, and domain-agnostic way to acqu…
Unsupervised-to-Online Reinforcement Learning
Junsu Kim, Seohong Park, Sergey Levine
Offline-to-online reinforcement learning (RL), a framework that trains a policy with offline RL and then further fine-tunes it with online RL, has been considered a promising recip…
Is Value Learning Really the Main Bottleneck in Offline RL?
Seohong Park, Kevin Frans, Sergey Levine +1
While imitation learning requires access to high-quality data, offline reinforcement learning (RL) should, in principle, perform similarly or better with substantially lower data q…
Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings
Kevin Frans, Seohong Park, Pieter Abbeel +1
Can we pre-train a generalist agent from a large amount of unlabeled offline trajectories such that it can be immediately adapted to any new downstream tasks in a zero-shot manner?…
Foundation Policies with Hilbert Representations
Seohong Park, Tobias Kreiman, Sergey Levine
Unsupervised and self-supervised objectives, such as next token prediction, have enabled pre-training generalist models from large amounts of unlabeled data. In reinforcement learn…
METRA: Scalable Unsupervised RL with Metric-Aware Abstraction
Seohong Park, Oleh Rybkin, Sergey Levine
Unsupervised pre-training strategies have proven to be highly effective in natural language processing and computer vision. Likewise, unsupervised reinforcement learning (RL) holds…
HIQL: Offline Goal-Conditioned RL with Latent States as Actions
Seohong Park, Dibya Ghosh, Benjamin Eysenbach +1
Unsupervised pre-training has recently become the bedrock for computer vision and natural language processing. In reinforcement learning (RL), goal-conditioned RL can potentially p…
Controllability-Aware Unsupervised Skill Discovery
Seohong Park, Kimin Lee, Youngwoon Lee +1
One of the key capabilities of intelligent agents is the ability to discover useful skills without external supervision. However, the current unsupervised skill discovery methods a…
Predictable MDP Abstraction for Unsupervised Model-Based RL
Seohong Park, Sergey Levine
A key component of model-based reinforcement learning (RL) is a dynamics model that predicts the outcomes of actions. Errors in this predictive model can degrade the performance of…
A Data Cartography based MixUp for Pre-trained Language Models
Seo Yeon Park, Cornelia Caragea
MixUp is a data augmentation strategy where additional samples are generated during training by combining random pairs of training samples and their labels. However, selecting rand…
On the Calibration of Pre-trained Language Models using Mixup Guided by Area Under the Margin and Saliency
Seo Yeon Park, Cornelia Caragea
A well-calibrated neural model produces confidence (probability outputs) closely approximated by the expected accuracy. While prior studies have shown that mixup training as a data…
Lipschitz-constrained Unsupervised Skill Discovery
Seohong Park, Jongwook Choi, Jaekyeom Kim +2
We study the problem of unsupervised skill discovery, whose goal is to learn a set of diverse and useful skills with no external reward. There have been a number of skill discovery…
Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods
Seohong Park, Jaekyeom Kim, Gunhee Kim
In reinforcement learning, continuous time is often discretized by a time scale , to which the resulting performance is known to be highly sensitive. In this work, we seek to fi…
Unsupervised Skill Discovery with Bottleneck Option Learning
Jaekyeom Kim, Seohong Park, Gunhee Kim
Having the ability to acquire inherent skills from environments without any external rewards or supervision like humans is an important problem. We propose a novel unsupervised ski…