Let ppo_continuous_action.pyonly run 1M steps (#161)

Author: vwxyzjn

cleanrl/ppo_continuous_action.py

@@ -37,7 +37,7 @@ def parse_args():
     # Algorithm specific arguments
     parser.add_argument("--env-id", type=str, default="HalfCheetahBulletEnv-v0",
         help="the id of the environment")
-    parser.add_argument("--total-timesteps", type=int, default=2000000,
+    parser.add_argument("--total-timesteps", type=int, default=1000000,
         help="total timesteps of the experiments")
     parser.add_argument("--learning-rate", type=float, default=3e-4,
         help="the learning rate of the optimizer")