https://github.com/MishaLaskin/rad/issues/9 中的tanslate参数设置
rad算法 https://github.com/MishaLaskin/rad/issues/9 中的translate aug中的script参数设置:
CUDA_VISIBLE_DEVICES=0 python train.py --domain_name cartpole --task_name swingup --encoder_type pixel --work_dir ./tmp/cartpole --action_repeat 8 --num_eval_episodes 10 --pre_transform_image_size 100 --image_size 84 --agent rad_sac --frame_stack 3 --data_augs translate --seed 23 --critic_lr 1e-3 --actor_lr 1e-3 --eval_freq 10000 --batch_size 128 --num_train_steps 200000 &
应改为:
CUDA_VISIBLE_DEVICES=0 python train.py --domain_name cartpole --task_name swingup --encoder_type pixel --work_dir ./tmp/cartpole --action_repeat 8 --num_eval_episodes 10 --pre_transform_image_size 64 --image_size 84 --agent rad_sac --frame_stack 3 --data_augs translate --seed 23 --critic_lr 1e-3 --actor_lr 1e-3 --eval_freq 10000 --batch_size 128 --num_train_steps 200000
PS:
pre_transform_image_size should be smaller than image_size. since the translate aug shifts the initially rendered image (which has size pre_transform_image_size) in a larger container (which has size image_size).