ard': 99.0, 'avg_steps': 29.13131313131313, 'success_rate': 0.
99}
{'iterations': 20, 'avg_reward': 98.0, 'avg_steps': 30.591836734693878,
'success_rate': 0.98}
{'iterations': 30, 'avg_reward': 98.0, 'avg_steps': 28.20408163265306,
'success_rate': 0.98}
{'iterations': 50, 'avg_reward': 95.0, 'avg_steps': 26.46315789473684,
'success_rate': 0.95}
{'iterations': 100, 'avg_reward': 95.0, 'avg_steps': 28.50526315789474,
'success_rate': 0.95}
{'iterations': 150, 'avg_reward': 95.0, 'avg_steps': 29.68421052631579,
'success_rate': 0.95}
{'iterations': 200, 'avg_reward': 97.0, 'avg_steps': 30.164948453608247,
'success_rate': 0.97}
{'iterations': 500, 'avg_reward': 97.0, 'avg_steps': 28.02061855670103,
'success_rate': 0.97}
{'iterations': 1000, 'avg_reward': 95.0, 'avg_steps': 28.16842105263158,
'success_rate': 0.95}
{'iterations': 1500, 'avg_reward': 99.0, 'avg_steps': 30.424242424242426,
'success_rate': 0.99}
————
running METNS
trials: 100, exploration_constant: 0.5, is_slippery: False
{'iterations': 1, 'avg_reward': -8.9, 'avg_steps': 8.0, 'success_rate': 0.01}
{'iterations': 2, 'avg_reward': 2.1, 'avg_steps': 12.363636363636363,
'success_rate': 0.11}
{'iterations': 3, 'avg_reward': 49.4, 'avg_steps': 22.14814814814815,
'success_rate': 0.54}
{'iterations': 5, 'avg_reward': 100.0, 'avg_steps': 17.26, 'success_rate': 1.0}
{'iterations': 10, 'avg_reward': 100.0, 'avg_steps': 14.96, 'success_rate': 1.0}
{'iterations': 20, 'avg_reward': 100.0, 'avg_steps': 14.16, 'success_rate': 1.0}
{'iterations': 30, 'avg_reward': 100.0, 'avg_steps': 14.54, 'success_rate': 1.0}
{'iterations': 50, 'avg_reward': 100.0, 'avg_steps': 16.72, 'success_rate': 1.0}
{'iterations': 100, 'avg_reward': 99.0, 'avg_steps': 26.848484848484848,
'success_rate': 0.99}
{'iterations': 150, 'avg_reward': 98.0, 'avg_steps': 32.857142857142854,
'success_rate': 0.98}
{'iterations': 200, 'avg_reward': 87.0, 'avg_ste
{'iterations': 200, 'avg_reward': 87.0, 'avg_ste