Suivre
Abhinav Verma
Titre
Citée par
Citée par
Année
Programmatically interpretable reinforcement learning
A Verma, V Murali, R Singh, P Kohli, S Chaudhuri
Thirty-fifth International Conference on Machine Learning (ICML), 2018
4082018
Imitation-projected programmatic reinforcement learning
A Verma, H Le, Y Yue, S Chaudhuri
Advances in Neural Information Processing Systems (NeurIPS), 15752-15763, 2019
942019
Control regularization for reduced variance reinforcement learning
R Cheng, A Verma, G Orosz, S Chaudhuri, Y Yue, JW Burdick
Thirty-sixth International Conference on Machine Learning (ICML), 2019
872019
Neurosymbolic Reinforcement Learning with Formally Verified Exploration
G Anderson, A Verma, I Dillig, S Chaudhuri
Advances in Neural Information Processing Systems (NeurIPS) 33, 2020
782020
Learning Differentiable Programs with Admissible Neural Heuristics
A Shah, E Zhan, J Sun, A Verma, Y Yue, S Chaudhuri
Advances in Neural Information Processing Systems (NeurIPS) 33, 2020
472020
Representing formal languages: A comparison between finite automata and recurrent neural networks
JJ Michalenko, A Shah, A Verma, RG Baraniuk, S Chaudhuri, AB Patel
International Conference on Learning Representations (ICLR), 2019
302019
Verifiable and interpretable reinforcement learning through program synthesis
A Verma
Proceedings of the AAAI Conference on Artificial Intelligence 33 (01), 9902-9903, 2019
72019
Compositional policy learning in stochastic control systems with formal guarantees
Đ Žikelić, M Lechner, A Verma, K Chatterjee, T Henzinger
Advances in Neural Information Processing Systems 36, 2024
32024
Eventual discounting temporal logic counterfactual experience replay
C Voloshin, A Verma, Y Yue
International Conference on Machine Learning, 35137-35150, 2023
32023
Deep Policy Optimization with Temporal Logic Constraints
A Shah, C Voloshin, C Yang, A Verma, S Chaudhuri, SA Seshia
arXiv preprint arXiv:2404.11578, 2024
12024
Programmatic reinforcement learning
A Verma
2021
Le système ne peut pas réaliser cette opération maintenant. Veuillez réessayer plus tard.
Articles 1–11