关注
Anurag Koul
Anurag Koul
PostDoctoral Researcher, Microsoft Research
在 oregonstate.edu 的电子邮件经过验证 - 首页
标题
引用次数
引用次数
年份
Visualizing and understanding atari agents
S Greydanus, A Koul, J Dodge, A Fern
International conference on machine learning, 1792-1801, 2018
3912018
Explainable Reinforcement Learning via Reward Decomposition
Z Juozapaitis, A Koul, A Fern, M Erwig, F Doshi-Velez
2222019
Learning finite state representations of recurrent policy networks
A Koul, S Greydanus, A Fern
arXiv preprint arXiv:1811.12530, 2018
932018
ma-gym: Collection of multi-agent environments based on OpenAI gym
A Koul
https://github.com/koulanurag/ma-gym, 2019
312019
Re-understanding finite-state representations of recurrent policy networks
MH Danesh, A Koul, A Fern, S Khorram
International Conference on Machine Learning, 2388-2397, 2021
232021
Explaining deep adaptive programs via reward decomposition
M Erwig, A Fern, M Murali, A Koul
IJCAI/ECAI workshop on explainable artificial intelligence, 2018
182018
Dream and search to control: Latent space planning for continuous control
A Koul, VV Kumar, A Fern, S Majumdar
arXiv preprint arXiv:2010.09832, 2020
42020
PcLast: Discovering Plannable Continuous Latent States
A Koul, S Sujit, S Chen, B Evans, L Wu, B Xu, R Chari, R Islam, R Seraj, ...
arXiv preprint arXiv:2311.03534, 2023
12023
Investigating Latent State and Uncertainty Representations in Reinforcement Learning
A Koul
2022
Offline Policy Comparison with Confidence: Benchmarks and Baselines
A Koul, M Phielipp, A Fern
arXiv preprint arXiv:2205.10739, 2022
2022
Towards Real-World Offline Reinforcement Learning
A Koul, J Dao, A Saxena, R Jayaraman
系统目前无法执行此操作，请稍后再试。
文章 1–11