A survey of data-driven and knowledge-aware explainable AI

XH Li, CC Cao, Y Shi, W Bai, H Gao… - … on Knowledge and …, 2020 - ieeexplore.ieee.org
We are witnessing a fast development of Artificial Intelligence (AI), but it becomes
dramatically challenging to explain AI models in the past decade.“Explanation” has a flexible …

Improving intrinsic exploration with language abstractions

J Mu, V Zhong, R Raileanu, M Jiang… - Advances in …, 2022 - proceedings.neurips.cc
Reinforcement learning (RL) agents are particularly hard to train when rewards are sparse.
One common solution is to use intrinsic rewards to encourage agents to explore their …

Learning with latent language

J Andreas, D Klein, S Levine - ar** pixels to rewards
P Goyal, S Niekum, R Mooney - Conference on Robot …, 2021 - proceedings.mlr.press
Reinforcement learning (RL), particularly in sparse reward settings, often requires
prohibitively large numbers of interactions with the environment, thereby limiting its …

Deep reinforcement learning for cooperative robots based on adaptive sentiment feedback

H Jeon, DW Kim, BY Kang - Expert Systems with Applications, 2024 - Elsevier
Human–robot cooperative tasks have gained importance with the emergence of robotics
and artificial intelligence technology. In interactive reinforcement learning techniques, robots …

Vlm agents generate their own memories: Distilling experience into embodied programs of thought

GH Sarch, L Jang, MJ Tarr, WW Cohen… - The Thirty-eighth …, 2024 - openreview.net
Large-scale generative language and vision-language models (LLMs and VLMs) excel in
few-shot in-context learning for decision making and instruction following. However, they …

Nnetscape navigator: Complex demonstrations for web agents without a demonstrator

S Murty, D Bahdanau, CD Manning - arxiv preprint arxiv:2410.02907, 2024 - arxiv.org
We introduce NNetscape Navigator (NNetnav), a method for training web agents entirely
through synthetic demonstrations. These demonstrations are collected by first interacting …

Learning to act with affordance-aware multimodal neural slam

Z Jia, K Lin, Y Zhao, Q Gao, G Thattai… - 2022 IEEE/RSJ …, 2022 - ieeexplore.ieee.org
Recent years have witnessed an emerging paradigm shift toward embodied artificial
intelligence, in which an agent must learn to solve challenging tasks by interacting with its …

Vlm agents generate their own memories: Distilling experience into embodied programs

G Sarch, L Jang, MJ Tarr, WW Cohen, K Marino… - arxiv preprint arxiv …, 2024 - arxiv.org
Large-scale generative language and vision-language models excel in in-context learning
for decision making. However, they require high-quality exemplar demonstrations to be …