search

Farama-Foundation / D4RL

A collection of reference environments for offline reinforcement learning
Apache License 2.0
1.32k stars 279 forks source link

BEAR Benchmark #33

Closed nkleber1 closed 4 years ago

nkleber1 commented 4 years ago

Hi Everyone

I am interested in benchmarking BEAR, but I cannot execute the corresponding script (antmaze_bear.py). I get the error message "No module named 'rlkit.torch.sac.bear'". Unfortunately I cannot find a module corresponding to BEAR anywhere else in the rlkit. Can anyone tell me where I can find this code or share their code with me?

Best regards Nils

aviralkumar2907 commented 4 years ago

Hi Nils,

All algorithms are now present in the d4rl_evaluations repo: https://github.com/rail-berkeley/d4rl_evaluations