diff --git a/PaddleRL/DeepQNetwork/train.py b/PaddleRL/DeepQNetwork/train.py index 04ee1ef143604aa16207d050da1af0f0c2a303a5..dd7986d704aec0c0948f81ca7ddd69bbbd3ea239 100644 --- a/PaddleRL/DeepQNetwork/train.py +++ b/PaddleRL/DeepQNetwork/train.py @@ -112,7 +112,7 @@ def train_agent(): while len(exp) < MEMORY_WARMUP_SIZE: total_reward, step = run_train_episode(agent, env, exp) pbar.update(step) - + # train test_flag = 0 save_flag = 0