issues Search Results · repo:sfujim/TD3_BC language:Python
Filter by
5 results
(72 ms)5 results
insfujim/TD3_BC (press backspace or delete to remove)Hello, want to know if this loss function -lmbda * Q.mean() + F.mse_loss(pi, action) setup is reasonable, because when Q
is greater than 0, the TD3 loss term becomes a constant, which essentially degenerates ...
stvsd1314
- Opened on Feb 13
- #5
Hi! I have the same question as a previously closed issue. I wasn t able to reproduce results for Antmaze tasks in
Table 8. I made the following adjustments in run_experiments.sh, 1. change envs to Antmaze; ...
Penguin0007
- Opened on Sep 5, 2024
- #4
kentwhfHi,
I would like to ask the setting about the experiments in Antmaze. Should I need to tune the hyparameters for mujoco
locomotion?
I find I cannot reproduce the results about Antmaze in the paper.
...
lucasliunju
- 1
- Opened on Nov 23, 2022
- #2
I run the code in halfcheetah-expert-v0, and it seems to work well, but its performance metric d4rl_score is only
about 1.1-1.2, and the result of the paper is about 110-120, I am confused. (my mujoco ...
TianQi-777
- 2
- Opened on Nov 13, 2021
- #1
Learn how you can use GitHub Issues to plan and track your work.
Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub IssuesProTip!
Press the /
key to activate the search input again and adjust your query.Learn how you can use GitHub Issues to plan and track your work.
Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub IssuesProTip!
Press the /
key to activate the search input again and adjust your query.