Reward Modulated STDP Breakout Example

[rizwanamunirk]

Hello!

I am running the "breakout_stdp.py" from breakout example and getting same number of spikes from all the output neurons. Moreover, the model is not learning even after 100 episode, the reward is still showing random values. Kindly help me in understanding the issue,

[Hananel-Hazan]

Could you plot the spike train so we can better visualize the input?

Additionally, could you provide more details on:

• Any modifications you've made to the original example
• The specific BindsNET version you're using
• Any error messages or unexpected behaviors you've encountered