Noise parameters in Reinforcement learning DDPG
84 views (last 30 days)
Show older comments
What should be the values of Noise parameters (for agent) if my action range is between -0.5 to -5 in DDPG reinforcement learning I want to explore whole action range for each sample time? Also is there anyway to make the noise options (for agent) independent of sample time?
0 Comments
Accepted Answer
Drew Davis
on 19 Jun 2019
Edited: Drew Davis
on 19 Jun 2019
Hi Surya
It is fairly common to have Variance*sqrt(SampleTime) somewhere between 1 and 10% of your action range for Ornstein Uhlenbeck (OU) action noise. So in your case, the variance can be set between 4.5*0.01/sqrt(SampleTime) and 4.5*0.10/sqrt(SampleTime). The other important factor is the VarianceDecayRate, which will dictate how fast the variance will decay. You can calculate how many samples it will take for your variance to be halved by this simple formula:
halflife = log(0.5)/log(1-VarianceDecayRate)
It is critically important for your agent to explore while learning so keeping the VarianceDecayRate small (or even zero) is a good idea. The other noise parameters can usually be left as default.
The sample time of the noise options will be inherited by the agent, so it is not necessary to configure. By default, the noise model will be queried at the same rate as the agent.
Hope this helps
Drew
5 Comments
More Answers (0)
See Also
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!