Pravin Game
Papers
1
Total Citations
2
H-Index
1
About
Pravin Game is a researcher at the intersection of artificial intelligence, reinforcement learning, and game-based simulation. His work focuses on developing and benchmarking algorithms that enable artificial agents to autonomously learn and perform complex tasks, particularly within dynamic 2D environments. His most-cited paper, "Playing a 2D Game Indefinitely using NEAT and Reinforcement Learning" (2022), addresses a critical challenge in AI: the need for robust, reproducible environments to test novel pathfinding and optimization algorithms. By combining NeuroEvolution of Augmenting Topologies (NEAT) with reinforcement learning, Game demonstrated a method for agents to sustain indefinite gameplay, offering a powerful framework for evaluating search space optimization. This contribution is especially relevant for robotics and autonomous systems, where real-world testing is costly. With 2 citations, this work has already begun influencing subsequent studies in evolutionary computation and adaptive learning. Game’s research provides a practical bridge between theoretical algorithm development and real-world application, making his work valuable for students and researchers exploring autonomous agent training and simulation-based AI testing.
Research Focus
Key Achievements
Top Papers
- 1Playing a 2D Game Indefinitely using NEAT and Reinforcement Learning2 citations · 2022