Pranjal Paliwal
Papers
1
Total Citations
4
H-Index
1
About
Pranjal Paliwal is a researcher advancing the frontiers of decentralized multi-agent systems and deep reinforcement learning (DRL) for robot swarms. His work directly confronts one of the field’s most persistent obstacles: non-stationarity, where concurrent policy updates among multiple agents destabilize learning. In his highly cited 2023 paper, “Decentralized Multi-Agent Reinforcement Learning with Global State Prediction,” Paliwal introduces a novel framework that enables individual robots to anticipate global state dynamics, effectively mitigating the instability that plagues traditional DRL in swarm contexts. This contribution has already garnered 4 citations, signaling its growing influence among peers tackling scalable, real-world multi-robot coordination. By bridging the gap between single-robot control successes and the complex demands of swarm intelligence, Paliwal’s work lays critical groundwork for applications in autonomous exploration, disaster response, and distributed manufacturing. His research not only addresses a fundamental theoretical challenge but also offers a practical pathway toward robust, decentralized decision-making in dynamic environments—a key achievement for a rising scholar in the field.
Research Focus
Key Achievements
Top Papers
- 1