bacow/easy-rl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
johnjim0816
2022-07-21 22:12:19 +08:00
parent 6b3121fcff
commit e9b3e92141
21 changed files with 99 additions and 85 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
codes/A2C/task0.py
View File

@@ -123,14 +123,15 @@ def train(cfg,envs):
loss.backward()
optimizer.step()
print('Finish training！')
return test_rewards, test_ma_rewards
return {'rewards':test_rewards,'ma_rewards':test_ma_rewards}
if __name__ == "__main__":
cfg = get_args()
envs = [make_envs(cfg.env_name) for i in range(cfg.n_envs)]
envs = SubprocVecEnv(envs)
# training
rewards,ma_rewards = train(cfg,envs)
res_dic = train(cfg,envs)
make_dir(cfg.result_path,cfg.model_path)
save_args(cfg)
save_results(rewards, ma_rewards, tag='train', path=cfg.result_path) # 保存结果
plot_rewards(rewards, ma_rewards, cfg, tag="train") # 画出结果
save_results(res_dic, tag='train',
path=cfg.result_path)
plot_rewards(res_dic['rewards'], res_dic['ma_rewards'], cfg, tag="train") # 画出结果