From 586b60315a348b503e37ca564d5bcc8e61f56543 Mon Sep 17 00:00:00 2001 From: Abhay Deshpande Date: Tue, 23 Apr 2024 16:58:10 -0700 Subject: [PATCH] Grammar and minor fixes --- index.html | 21 ++++++++++++++------- 1 file changed, 14 insertions(+), 7 deletions(-) diff --git a/index.html b/index.html index e471b27..557ee56 100644 --- a/index.html +++ b/index.html @@ -214,7 +214,15 @@

Data Efficient Behavior Cloning for Fine Man

Abstract

- We stuy imitation learning to teach robots from expert demonstrations. During robots' execution, compounding errors from hardware noise and external disturbances, coupled with incomplete data coverage, can drive the agent into unfamiliar states and cause unpredictable behaviors. To address this challenge, we propose a framework, CCIL: Continuity-based data augmentation for Corrective Imitation Learning. It leverages the local continuity inherent in dynamic systems to synthesize corrective labels. CCIL learns a dynamics model from the expert data and uses it to generate labels guiding the agent back to expert states. Our approach makes minimal assumptions, requiring neither expert re-labeling nor ground truth dynamics models. By exploiting local continuity, we derive provable bounds on the errors of the synthesized labels. Through evaluations across diverse robotic domains in simulation and the real world, we demonstrate CCIL's effectiveness in improving imitation learning performance. + We study imitation learning to teach robots from expert demonstrations. During robots' execution, compounding errors + from hardware noise and external disturbances, coupled with incomplete data coverage, can drive the agent into + unfamiliar states and cause unpredictable behavior. To address this challenge, we propose a framework, CCIL: + Continuity-based data augmentation for Corrective Imitation Learning. It leverages the local continuity inherent in + dynamic systems to synthesize corrective labels. CCIL learns a dynamics model from the expert data and uses it to + generate labels guiding the agent back to expert states. Our approach makes minimal assumptions, requiring neither + expert re-labeling nor ground truth dynamics models. By exploiting local continuity, we derive provable bounds on the + errors of the synthesized labels. Through evaluations across diverse robotic domains in simulation and the real world, + we demonstrate CCIL's effectiveness in improving imitation learning performance.

@@ -462,7 +470,7 @@

CCIL improves imitation learning, especially in low-data

- CCIL can bring in prominent performance boost in low-data regimes compared to using standard behavior cloning, showcasing + CCIL can yield a prominent performance boost in low-data regimes compared to using standard behavior cloning, showcasing its data efficiency and robustness.

@@ -479,12 +487,11 @@

CCIL's Robustness to Lipschitz Constraint

- CCIL makes a critical assumption that the system dynamics contain local continuity. In practice, however, its application is relatively insensitive to the hyper-parameter choice of Lipschitz constraint in learning the dynamics model. As long as we filter generated labels using appropriate label error threshold, CCIL could yield a significant performance boost. + CCIL makes a critical assumption that the system dynamics contain local continuity. In practice, however, its + application is relatively insensitive to the hyper-parameter choice of Lipschitz constraint in learning the dynamics + model. As long as we filter generated labels using appropriate label error threshold, CCIL could yield a significant + performance boost.

-