Hi,
I have a question about the entropy coefficient c2 of PPO and its standard value in SIMPLE.
In the original paper, the "standard" value is c2=0.01 but in SIMPLE its set to c2=0.1
"parser.add_argument("--entcoeff", "-ent", type = float, default = 0.1, help="The entropy coefficient in PPO")"
Is there a reason to put the standard value so high in SIMPLE? I am currently trying to tune that value and I am just curious.
Kind regards,
Markus
(Paper: https://arxiv.org/pdf/1707.06347.pdf)
Hi,
I have a question about the entropy coefficient c2 of PPO and its standard value in SIMPLE.
In the original paper, the "standard" value is c2=0.01 but in SIMPLE its set to c2=0.1
"parser.add_argument("--entcoeff", "-ent", type = float, default = 0.1, help="The entropy coefficient in PPO")"
Is there a reason to put the standard value so high in SIMPLE? I am currently trying to tune that value and I am just curious.
Kind regards,
Markus
(Paper: https://arxiv.org/pdf/1707.06347.pdf)