Pavan Samtani — accepted AI-conference papers

2023

Learning to Break Rocks With Deep Reinforcement Learning

Pavan Samtani, Francisco Leiva, Javier Ruiz-del-Solar

RA-L 2023

This work proposes a scheme for learning how to break rocks with an impact hammer. The problem is formulated as a Partially Observable Markov's Decision Process, and then solved through deep reinforcement learning. We propose a simple formulation, requiring only a basic sensorization of the hammer's

Cited by 13 Source ↗Scholar ↗

2021

Learning to Play Soccer From Scratch: Sample-Efficient Emergent Coordination Through Curriculum-Learning and Competition

Pavan Samtani, Francisco Leiva, Javier Ruiz-del-Solar

IROS 2021poster

This work proposes a scheme that allows learning complex multi-agent behaviors in a sample efficient manner, applied to 2v2 soccer. The problem is formulated as a Markov game, and solved using deep reinforcement learning. We propose a basic multi-agent extension of TD3 for learning the policy of eac…

Cited by 5 Source ↗code ↗Scholar ↗