Follow
Bharat Prakash
Title
Cited by
Cited by
Year
Improving safety in reinforcement learning using model-based architectures and human intervention
B Prakash, M Khatwani, N Waytowich, T Mohsenin
The Thirty-Second International Flairs Conference, 2019
152019
On the use of deep autoencoders for efficient embedded reinforcement learning
B Prakash, M Horton, NR Waytowich, WD Hairston, T Oates, T Mohsenin
Proceedings of the 2019 on Great Lakes Symposium on VLSI, 507-512, 2019
122019
Guiding Safe Reinforcement Learning Policies Using Structured Language Constraints
B Prakash, N Waytowich, A Ganesan, T Oates, T Mohsenin
UMBC Student Collection, 2020
112020
An energy efficient edgeai autoencoder accelerator for reinforcement learning
NK Manjunath, A Shiri, M Hosseini, B Prakash, NR Waytowich, ...
IEEE Open Journal of Circuits and Systems 2, 182-195, 2021
72021
Combining Learning from Human Feedback and Knowledge Engineering to Solve Hierarchical Tasks in Minecraft
VG Goecks, N Waytowich, D Watkins, B Prakash
arXiv preprint arXiv:2112.03482, 2021
52021
Cyclic sparsely connected architectures for compact deep convolutional neural networks
M Hosseini, NK Manjunath, B Prakash, A Mazumder, V Chandrareddy, ...
IEEE Transactions on Very Large Scale Integration (VLSI) Systems 29 (10 …, 2021
42021
Interactive Hierarchical Guidance using Language
B Prakash, N Waytowich, T Oates, T Mohsenin
arXiv preprint arXiv:2110.04649, 2021
22021
Retrospective on the 2021 MineRL BASALT Competition on Learning from Human Feedback
R Shah, SH Wang, C Wild, S Milani, A Kanervisto, VG Goecks, ...
NeurIPS 2021 Competitions and Demonstrations Track, 259-272, 2022
12022
Automatic Goal Generation using Dynamical Distance Learning
B Prakash, N Waytowich, T Mohsenin, T Oates
arXiv preprint arXiv:2111.04120, 2021
2021
The system can't perform the operation now. Try again later.
Articles 1–9