Last call to make your voice heard! Our 2022 Developer Survey closes in less than a week. Take survey.

New answers tagged

0 votes

How to model a multi-agent reinforcement learning problem where actions of different agents can take different durations?

" ... how I would be able to model a multi-agent reinforcement learning problem when each agent performing an action would take different durations to complete the action. ... where vehicles on a ...
user avatar
  • 396
1 vote
Accepted

PPO custom implementation: do metrics like value loss, actor loss and entropy move a certain way?

It's difficult to tell how the output of the loss changes over the course of the experiment as you use them as a measure on how well your model performs. Ideally, the loss decreases over time with ...
user avatar
2 votes

Why is training longer not better in reinforcement learning?

Could it be due to catastrophic forgetting/interference? If once the agent reaches 320K steps it becomes good at the task, it might start to experience only success. This could cause the agent to ...
user avatar
0 votes
Accepted

How does PPO account for the last reward?

I actually feel kinda dumb writing this, but the update is made if the TOTAL environment steps is a multiple of the time horizon. I did, recode my PPO algorithm, and it seems to eventually solve the ...
user avatar

Top 50 recent answers are included