paper-with-me

홈 › Papers

Efficient Policy Adaptation with Contrastive Prompt Ensemble for Embodied Agents

2024-12-16 · NeurIPS 2023 11 · Wonje Choi, Woo Kyung Kim, SeungHyun Kim, Honguk Woo

For embodied reinforcement learning (RL) agents interacting with the environment, it is desirable to have rapid policy adaptation to unseen visual observations, but achieving zero-shot adaptation capability is considered as a challenging problem in the RL context. To address the problem, we present a novel contrastive prompt ensemble (ConPE) framework which utilizes a pretrained vision-language model and a set of visual prompts, thus enabling efficient policy learning and adaptation upon a wide range of environmental and physical changes encountered by embodied agents. Specifically, we devise a guided-attention-based ensemble approach with multiple visual prompts on the vision-language model to construct robust state representations. Each prompt is contrastively learned in terms of an individual domain factor that significantly affects the agent's egocentric perception and observation. For a given task, the attention-based ensemble and policy are jointly learned so that the resulting state representations not only generalize to various domains but are also optimized for learning the task. Through experiments, we show that ConPE outperforms other state-of-the-art algorithms for several embodied agent tasks including navigation in AI2THOR, manipulation in egocentric-Metaworld, and autonomous driving in CARLA, while also improving the sample efficiency of policy learning and adaptation.

📄 PDF Abstract BibTeX arXiv:2412.11484

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingLanguage ModelingLanguage ModellingReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Entropy Regularization 설명 없음
PPO Proximal Policy Optimization, or PPO, is a policy gradient method for reinforcement learning. The motivation was to have an algorithm with the data efficiency and reliable…
CARLA CARLA is an open-source simulator for autonomous driving research. CARLA has been developed from the ground up to support development, training, and validation of autonomous urban…

Similar Papers 제목 키워드 기반

Learning Adaptive Cross-Embodiment Visuomotor Policy with Contrastive Prompt Orchestration

2026-02-01 · Yuhang Zhang, Chao Yan, Jiaxi Yu, Jiaping Xiao 외 arxiv

Learning adaptive visuomotor policies for embodied agents remains a formidable challenge, particularly when facing cross-embodiment variations such as diverse sensor configurations and dynamic properties. Conventional le…

Contrastive Learning

Embodied CoT Distillation From LLM To Off-the-shelf Agents

2024-12-16 · Wonje Choi, Woo Kyung Kim, Minjong Yoo, Honguk Woo

We address the challenge of utilizing large language models (LLMs) for complex embodied tasks, in the environment where decision-making systems operate timely on capacity-limited, off-the-shelf devices. We present DeDer,…

Decision MakingIn-Context LearningLanguage ModelingLanguage Modelling+1

GenRL: Multimodal-foundation world models for generalization in embodied agents

2024-06-26 · Pietro Mazzaglia, Tim Verbelen, Bart Dhoedt, Aaron Courville 외

Learning generalist embodied agents, able to solve multitudes of tasks in different domains is a long-standing problem. Reinforcement learning (RL) is hard to scale up as it requires a complex reward design for each task…

BenchmarkingReinforcement Learning (RL)

Dual-Granularity Contrastive Reward via Generated Episodic Guidance for Efficient Embodied RL

2026-02-13 · Xin Liu, Yixuan Li, Yuhui Chen, Yuxing Qin 외 arxiv

Designing suitable rewards poses a significant challenge in reinforcement learning (RL), especially for embodied manipulation. Trajectory success rewards are suitable for human judges or model fitting, but the sparsity s…

Reinforcement LearningDomain AdaptationVideo Generation

LLM-Based Offline Learning for Embodied Agents via Consistency-Guided Reward Ensemble

2024-11-26 · Yujeong Lee, Sangwoo Shin, Wei-Jin Park, Honguk Woo

Employing large language models (LLMs) to enable embodied agents has become popular, yet it presents several limitations in practice. In this work, rather than using LLMs directly as agents, we explore their use as tools…

Offline RLReinforcement Learning (RL)