-
Does the random-expert dataset used in CQL paper publish for Hopper, Walke2d and Halfcheetah? Thanks!
-
Thank you for sharing codes.
when I run " python3 spirl/train.py --path=spirl/configs/skill_prior_learning/kitchen/flat --val_data_size=160 "
I encounter error like this:
"
Could not find cal…
-
I encounter error like this:
Traceback (most recent call last):
File "spirl/rl/train.py", line 311, in
RLTrainer(args=get_args())
File "spirl/rl/train.py", line 76, in __init__
self.…
-
I believe I discovered a potential error for hopper in D4RL (I've fetched the latest version of the dataset). I printed out the number of terminals and timeouts, and calculated per trajectory reward a…
-
https://github.com/aviralkumar2907/CQL/blob/d67dbe9cf5d2b96e3b462b6146f249b3d6569796/d4rl/rlkit/torch/sac/cql.py#L241
`q1_next_actions = self._get_tensor_values(obs, new_curr_actions_tensor, network=…
-
Hello, I'm noticing that the expert data is of very low quality as shown below. Could the datasets be incorrect, or am I processing the data incorrectly? Thanks!
```
import gym
import d4rl
impor…
-
First of all, thank you for creating such a great library.
**Describe the bug**
I am running online training with DQN on gym atari environment. But I guess because of hardcoded part, observation s…
-
Hi,
Thanks so much for your work. I have a question about the normalization of results. Specifically, e.g., in the Gym domain, each result is normalized according to the expert-policy (sac) and ran…
-
Hi, thank you for providing such a great work. I have some question about the data collection method. I look through the code, and find this may be relevant:
https://github.com/rail-berkeley/d4rl/b…
-
hi I want to test the case in kitchen,but I get a error,can you help me?thanks very much!
```
Python 3.7.8 | packaged by conda-forge | (default, Jul 31 2020, 02:25:08)
[GCC 7.5.0] on linux
Type "…