Samyak Parajuli
Papers
1
Total Citations
3
H-Index
1
About
Samyak Parajuli is a researcher advancing the frontiers of artificial intelligence, with a primary focus on hierarchical reinforcement learning (HRL) and multi-agent systems. His most-cited work, "Inter-Level Cooperation in Hierarchical Reinforcement Learning" (2019), tackles a critical bottleneck in AI: enabling structured exploration for complex, long-term planning problems. Parajuli proposed a novel end-to-end training paradigm that fosters cooperation between temporally decoupled policy levels, addressing the long-standing challenge of training multi-level hierarchies effectively. This contribution has garnered 3 citations, laying groundwork for more robust and scalable AI agents. Beyond this, his research explores how agents can learn to coordinate and decompose tasks autonomously, with implications for robotics and game AI. Parajuli’s work is notable for its focus on practical, trainable architectures that bridge theory and application, making him a promising voice in the push toward more intelligent, hierarchical decision-making systems.
Research Focus
Key Achievements
Top Papers
- 1Inter-Level Cooperation in Hierarchical Reinforcement Learning3 citations · 2019