Revision history [back]

Hi all,

I am working on integrating E+ with OpenAI Gym to train reinforcement learning agents. When using the new runtime API, I am getting an error when trying to run multiple simulations (see screenshot on link below - cannot upload files yet as I'm new on the forum).

https://www.dropbox.com/s/yrjhv0n7w1d8mql/screenshot.png?dl=0

The documentation says to run clear_callbacks before making multiple runs - but it doesn't make any effect.

Some people ran the simulation in a different process and communicated through pipes but I would like to use new API callback features to simplify the process.

Any hint about what is going on?

Thanks in advance,

Hi all,

I am working on integrating E+ with OpenAI Gym to train reinforcement learning agents. When using the new runtime API, I am getting an error when trying to run multiple simulations (see screenshot on link below - cannot upload files yet as I'm new on the forum).

https://www.dropbox.com/s/yrjhv0n7w1d8mql/screenshot.png?dl=0simulations.

The documentation says to run clear_callbacks before making multiple runs - but it doesn't make any effect.

Some people ran the simulation in a different process and communicated through pipes but I would like to use new API callback features to simplify the process.

Any hint about what is going on?

Thanks in advance,

Hi all,

I am working on integrating E+ with OpenAI Gym to train reinforcement learning agents. When using the new runtime API, I am getting an error when trying to run multiple simulations.

The documentation says to run clear_callbacks before making multiple runs - but it doesn't make any effect.

Some people ran the simulation in a different process and communicated through pipes but I would like to use new API callback features to simplify the process.

Any hint about what is going on?

Thanks in advance,

Hi all,

I am working on integrating E+ with OpenAI Gym to train reinforcement learning agents. When using the new runtime API, I am getting an error when trying to run multiple simulations.

The documentation says to run clear_callbacks before making multiple runs - but it doesn't make any effect.

Some people ran the simulation in a different process and communicated through pipes but I would like to use new API callback features to simplify the process.

Any hint about what is going on?

Thanks in advance,