diff --git a/config/gail_config.yaml b/config/gail_config.yaml index 7a4e4b3a00..fae274597b 100644 --- a/config/gail_config.yaml +++ b/config/gail_config.yaml @@ -7,7 +7,7 @@ default: hidden_units: 128 lambd: 0.95 learning_rate: 3.0e-4 - max_steps: 5.0e4 + max_steps: 5.0e5 memory_size: 256 normalize: false num_epoch: 3 diff --git a/config/trainer_config.yaml b/config/trainer_config.yaml index ded53eb56c..313230fab2 100644 --- a/config/trainer_config.yaml +++ b/config/trainer_config.yaml @@ -120,7 +120,7 @@ VisualPyramids: buffer_size: 12000 summary_freq: 12000 time_horizon: 1000 - max_steps: 5.0e5 + max_steps: 5.0e6 beta: 0.001 reward_signals: extrinsic: