search

davide97l / rl-policies-attacks-defenses

Adversarial attacks on Deep Reinforcement Learning (RL)
MIT License
75 stars 12 forks source link

Test DAM metric on Atari environments #3

Open davide97l opened 4 years ago

davide97l commented 4 years ago
davide97l commented 4 years ago

To be tested on a trained policy

GongYanfu commented 2 years ago

After installed the dependencies in the requirements.txt, Can you run this command bellow: python atari_dqn.py --resume_path "log/PongNoFrameskip-v4/dqn/policy.pth" --watch --test_num 10 --task "PongNoFrameskip-v4"

For me, there is a problem as below: gym.error.NameNotFound: Environment PongNoFrameskip doesn't exist.

GongYanfu commented 1 year ago

Hi, Do you know the paper of critical strategy attack? image

davide97l commented 1 year ago

Hello, critical strategy attack is an algorithm developed by me, that's why it can't be found online. However, you can read about it in my thesis work.

GongYanfu commented 1 year ago

🆗 thanks a lot

---- Replied Message ---- | From | Davide @.> | | Date | 10/10/2022 12:19 | | To | @.> | | Cc | @.**@.> | | Subject | Re: [davide97l/rl-policies-attacks-defenses] Test DAM metric on Atari environments (#3) |

Hello, critical strategy attack is an algorithm developed by me, that's why it can't be found online. However, you can read about it in my thesis work.

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.***>