-
Meta-World was designed to be both a Meta-RL and a Multi-Task RL benchmark.
One of the awkward consequences of that is that the way goal conditioning is handled is very complicated in Meta-World.
**…
-
Hi, I have tried to set the num_envs and nminibatches both to 1 and this error still happens. How large is your GPU memory? I am using 4GB currently. Or is this caused by another problem?
-
-
Since HER applies to any off policy algorithm, I think this would be useful for researchers studying sparse reward problems.
I can take a crack at this and submit a PR. Let me know what you think …
-
Thanks for your repository.
I am trying to train RIG using the following command:
`~/rlkit-0.1.2$ python3.6 examples/rig/pusher/rig.py
`
the training proceeds, but can I visualize it as well?
…
-
Hi! Sorry to bother you again, but I am still confused about some experiment settings. I see there are some parameters in df_planning.yaml that control the episode_len, x_shape, frame_stack, and horiz…
hw-du updated
1 month ago
-
Dear @gtikhonov ,
I am having a similar problem trying to sampleMcmc a model 2 random effects, one that was the spatial coordinates and the other a regional categorical variable. Since I have >1000…
-
Without guidance, the performance greatly drops. Does you observation contain the goal state? The guidance with distance to goal seems to be too strong--the gradients itself may lead to good results.
-
### Zoom webinar: https://navercorp.zoom.us/j/92208940283
### News
- 6.25 73주년 순국선열들의 희생에 감사드립니다.
- Conferences
- EMNLP 2023 deadline: 모두 수고하셨습니다.
- CVPR 2023: 모두들 의미있는 학회 보내셨나요~
- Best …
-
Hi, I'm new to diffusion models in RL and am trying to figure out how the diffuser works particularly with conditioning and was hoping I can get some guidance. I read the paper and it proposes the ide…