Reinforcement Learning for Pendulum Control
Built PyTorch agents for swing-up and stabilization, achieving 90% success in the reported noisy single-pendulum simulations.
Learning to Swing Up and Catch
I developed PyTorch reinforcement-learning agents for single-pendulum swing-up and stabilization. The controller separated the energy-building swing from the final catch, with reward functions tailored to each stage. This made the transition into upright balance a central part of policy design.
The experiments compared discrete and continuous-control methods, including DQN, DDPG, and PPO, with training curves and trajectory visualizations used to diagnose behavior.
Simulation Results
The reported single-pendulum runs achieved 100% swing-up and stabilization success under ideal conditions and 90% under noisy conditions over 30-second simulations. The broader project also stabilized a double pendulum, although model-free swing-up remained unresolved.
Single-pendulum swing-up from rest
Single-pendulum swing-up under noisy conditions
Double-pendulum stabilization