Amit Yadav
Home
Experience
Projects
Blog
Contact
RL
Reinforcement Learning for Temporal Logic Goal
Reward engineering for RL algorithms using temporal logic constraints
Reinforcement Learning Based Control of Quadrotor
To control a quadrotor with a neural network trained using RL techniques
Autonomous Atari game Player
Implmented Deep Determininstic Policy Gradient to train a autonomous game player.
Cite
×