clean up config

config/trainer_config.yaml

     num_layers: 2
     normalize: false
 
-# BigWallJumpLearning:
-#     max_steps: 1.0e6
-#     batch_size: 128
-#     buffer_size: 2048
-#     beta: 5.0e-3
-#     hidden_units: 256
-#     summary_freq: 2000
-#     time_horizon: 128
-#     num_layers: 2
-#     normalize: false
-
 BigWallJumpLearning:
     normalize: true
     num_epoch: 8
             strength: 0.02
             gamma: 0.99
             encoding_size: 256
-
-# BigWallJumpLearning:
-#     normalize: true
-#     num_epoch: 3
-#     time_horizon: 1000
-#     batch_size: 2024
-#     buffer_size: 20240
-#     max_steps: 1e6
-#     summary_freq: 3000
-#     num_layers: 3
-#     hidden_units: 512
-#     reward_signals:
-#         extrinsic:
-#             strength: 1.0
-#             gamma: 0.99
-#         curiosity:
-#             strength: 0.02
-#             gamma: 0.99
-#             encoding_size: 256
-
 
 StrikerLearning:
     max_steps: 5.0e5