lack of Ant-v2 task related

Question

lack of Ant-v2 task related

Opened this issue a year ago · 6 comments

Hello,

I am wondering learning results of Ant-v2's dataset, like ant-random-v0/2 ant-medium-v0/v2. I think it is not listed in d4RL original paper but it's supplemented in github later.

Do you have the interest to evaluate thoes ant-* environment? Cuz I get very strange result for ant, even ant-random gives great result. So I am curious to compare with your result.

Best,

Answer 1 · 2023-11-08T15:26:55.000Z

@im-Kitsch Hi, thanks for the issue. It takes long to benchmark all algorithms with Ant dataset. But, if you give me which algorithm you want me to test, I can prioritize it.

Answer 2 · 2023-11-08T16:13:26.000Z

Hi, thnks a lot for the kind replay. Personally I am interesting on AWAC or BCQ.

Thanks!

Answer 3 · 2023-11-08T16:52:00.000Z

Okay, I started BCQ benchmark with ant-x-v0 dataset first. I'll be back to you later once I get results.

Answer 4 · 2023-11-18T03:28:55.000Z

@im-Kitsch Sorry, it took time, but I've added BCQ results with ant-x-v0 datasets.
https://github.com/takuseno/d3rlpy-benchmarks/blob/main/d4rl_table.csv

Answer 5 · 2023-11-28T12:33:22.000Z

I've added v2 dataset results as well.

Answer 6 · 2023-12-03T21:08:44.000Z

cool, @takuseno , really thanks a lot, it's really helpful