SORL:
python cleanrl/stylev2_env_lora_final.py --offline_dir2 /home/wjh/myh/cleanrl-master/useful_models/buffer_onlyshoot_cai --load_q /home/wjh/myh/cleanrl-master/useful_models/load_q_offline/dqn_env_offline_500000.cleanrl_model --total-timesteps 100010

EM:
python cleanrl/stylev2_env_lora_final_eval_cls.py --offline_dir2 /home/wjh/myh/cleanrl-master/useful_models/buffer_onlyshoot_cai --load_q /home/wjh/myh/cleanrl-master/useful_models/load_q_offline/dqn_env_offline_500000.cleanrl_model --total-timesteps 100010

Off-RLPMM:
python cleanrl/stylev2_env_lora_final_01.py --offline_dir2 /home/wjh/myh/cleanrl-master/useful_models/buffer_onlyshoot_cai --load_q /home/wjh/myh/cleanrl-master/useful_models/load_q_offline/dqn_env_offline_500000.cleanrl_model --total-timesteps 100010

InfoGAIL:
python cleanrl/style_env.py --offline_dir2 /home/wjh/myh/cleanrl-master/useful_models/buffer_onlyshoot_cai