Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings

1 code implementation • 27 Feb 2024 • Kevin Frans, Seohong Park, Pieter Abbeel, Sergey Levine

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?

Offline RL reinforcement-learning

Foundation Policies with Hilbert Representations

1 code implementation • 23 Feb 2024 • Seohong Park, Tobias Kreiman, Sergey Levine

While a number of methods have been proposed to enable generic self-supervised RL, based on principles such as goal-conditioned RL, behavioral cloning, and unsupervised skill learning, such methods remain limited in terms of either the diversity of the discovered behaviors, the need for high-quality demonstration data, or the lack of a clear prompting or adaptation mechanism for downstream tasks.

Reinforcement Learning (RL) Unsupervised Pre-training

METRA: Scalable Unsupervised RL with Metric-Aware Abstraction

1 code implementation • 13 Oct 2023 • Seohong Park, Oleh Rybkin, Sergey Levine

Through our experiments in five locomotion and manipulation environments, we demonstrate that METRA can discover a variety of useful behaviors even in complex, pixel-based environments, being the first unsupervised RL method that discovers diverse locomotion behaviors in pixel-based Quadruped and Humanoid.

Reinforcement Learning (RL) Unsupervised Pre-training +1

HIQL: Offline Goal-Conditioned RL with Latent States as Actions

1 code implementation • NeurIPS 2023 • Seohong Park, Dibya Ghosh, Benjamin Eysenbach, Sergey Levine

This structure can be very useful, as assessing the quality of actions for nearby goals is typically easier than for more distant goals.

Reinforcement Learning (RL) Unsupervised Pre-training

Controllability-Aware Unsupervised Skill Discovery

3 code implementations • 10 Feb 2023 • Seohong Park, Kimin Lee, Youngwoon Lee, Pieter Abbeel

One of the key capabilities of intelligent agents is the ability to discover useful skills without external supervision.

Predictable MDP Abstraction for Unsupervised Model-Based RL

2 code implementations • 8 Feb 2023 • Seohong Park, Sergey Levine

A key component of model-based reinforcement learning (RL) is a dynamics model that predicts the outcomes of actions.

Model-based Reinforcement Learning Reinforcement Learning (RL)

Lipschitz-constrained Unsupervised Skill Discovery

no code implementations • ICLR 2022 • Seohong Park, Jongwook Choi, Jaekyeom Kim, Honglak Lee, Gunhee Kim

To address this issue, we propose Lipschitz-constrained Skill Discovery (LSD), which encourages the agent to discover more diverse, dynamic, and far-reaching skills.

Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods

1 code implementation • NeurIPS 2021 • Seohong Park, Jaekyeom Kim, Gunhee Kim

SAR can handle the stochasticity of environments by adaptively reacting to changes in states during action repetition.

Policy Gradient Methods

Unsupervised Skill Discovery with Bottleneck Option Learning

1 code implementation • 27 Jun 2021 • 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.

Disentanglement