deep-active-inference-mc
                                
                                
                                
                                    deep-active-inference-mc copied to clipboard
                            
                            
                            
                        Deep active inference agents using Monte-Carlo methods
I am having trouble understanding why for term 1, the sum is taken between the two computed entropy terms: https://github.com/zfountas/deep-active-inference-mc/blob/c40ef0dd9c16c4d98abfa1f9392d9777f1899dc9/src/tfmodel.py#L343-L344 I understand this gives the sum of two entropy terms...
In the scientific article there is talk about Agent trained in the Animal-AI environment. How can I accomplish this. I tried installing animal-ai environment but it didn't work.
I am using 1. Geforce 3060 Ti 2. tensorflow-gpu 2.4.0 3. python3.7 4. CUDA 11.0 5. cudnn 8.0 when trying to run train.py, the error messages show some problems with...