artifacts/improved_ppo_run.csv

step,reward,length
200,-5.55,200
400,-4.01,200
600,-4.25,200
800,-5.47,200
1000,-5.18,200
1200,-4.5,200
1400,-6.79,200
1600,-4.45,200
1800,-3.92,200
2000,-6.3,200