0 Follower
0 Following
qdenisq
Location
Badges
1
1
1
Activity
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
Dec
Jan
Feb
Mar
Apr
Mon
Wed
Fri
Ratings Progression
Loading...
Challenge Categories
Loading...
Challenges Entered
Reinforcement Learning on Musculoskeletal Models
Latest submissions
See Allgraded | 17307 | ||
failed | 17306 | ||
failed | 17305 |
Sample-efficient reinforcement learning in Minecraft
Latest submissions
Participant | Rating |
---|
Participant | Rating |
---|
NeurIPS 2019: Learn to Move - Walk Around
Velocity target explanation
Almost 5 years agoHi there, could organizers elaborate on the velocity target map? What does it tell us about?
Thanks in advance
qdenisq has not provided any information yet.
Environment slowing down?
Almost 5 years agoHi,
Am I the only one who has the issue with the environment provided that it slows down over time? For example, the first 50k steps on my machine took around 4k seconds while the same number of steps from 200k to 250k took almost 10k seconds. Is this a known issue? Would like to hear back from organizers with some ideas on how to fix properly. Right now I have to kill the process simbody and restart it, letβs say, every 100k steps, which is a quite dirty workaround.
Cheers.