search

sail-sg / envpool

C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.
https://envpool.readthedocs.io
Apache License 2.0
1.08k stars 99 forks source link

[BUG] no Acc-v3 environment #66

Closed 963141377 closed 2 years ago

963141377 commented 2 years ago

Describe the bug

A clear and concise description of what the bug is.

When using tianshou, there's no Acc-v3 environment.

File "test_dqn_acc.py", line 246, in Acc_tain() File "test_dqn_acc.py", line 112, in Acc_tain args.task, num_envs=args.training_num, env_type="gym" File "/home/zhulin/.conda/envs/mytorch/lib/python3.7/site-packages/envpool/registration.py", line 43, in make f"{task_id} is not supported, envpool.list_all_envs() may help." AssertionError: Acc-v3 is not supported, envpool.list_all_envs() may help.

Trinkle23897 commented 2 years ago

There's no Acc-v3 in either gym or tianshou's example. Is that your customized env?

963141377 commented 2 years ago

yes, my customized env. how can I use it?

Trinkle23897 commented 2 years ago

https://envpool.readthedocs.io/en/latest/pages/env.html

963141377 commented 2 years ago

Thank you very much.

Trinkle23897 commented 2 years ago

BTW, if you only look for a fast prototype, it's better to use python vectorized env first (see here).