igpaub
/

dqn-QbertNoFrameskip-v4

Reinforcement Learning

stable-baselines3

QbertNoFrameskip-v4

deep-reinforcement-learning

Model card Files Files and versions Community

igpaub commited on Nov 6, 2023

Commit

0085fd2

•

1 Parent(s): 800379c

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -73,7 +73,7 @@ OrderedDict([('batch_size', 32),
              ('gradient_steps', 1),
              ('learning_rate', 0.0001),
              ('learning_starts', 100000),
-             ('n_timesteps', 10000000.0),
              ('optimize_memory_usage', False),
              ('policy', 'CnnPolicy'),
              ('target_update_interval', 1000),

              ('gradient_steps', 1),
              ('learning_rate', 0.0001),
              ('learning_starts', 100000),
+             ('n_timesteps', 3000000.0),
              ('optimize_memory_usage', False),
              ('policy', 'CnnPolicy'),
              ('target_update_interval', 1000),