ai-traineree

ai-traineree copied to clipboard

What is the best way to reshape the observation before feedint it to the network?

1

Hi Dawid, I am trying to do an example for Sneks. However, the default network (FcNet) only accepts 1 dim as an input shape. In the game, we have an...

LuisFMCuriel

Assertion failed for multi-agent environment

2

Hi, I am working with the example [code](https://github.com/laszukdawid/ai-traineree/blob/master/examples/petting_zoo/connect_four.py) for the training of multi-agent env. However, when I create each agent, the expected input for the network is one dimension `assert...

LuisFMCuriel

Curiousity in PPO

2

## What Add Curiosity driven exploration to PPO. ## Why It's been shown [citation needed] that Curiosity improves agents' performance on sparse reward environments.

laszukdawid

## What Each agent has built-in epsilon greedy mechanism. There's likely little need to have the same code everywhere so it should be moved to a single place. ## Consideration...

laszukdawid

Unity Environment

3

Hey, I am glad I ran into your repository from the mlagents threads. How could I use your project to import my unity environment? I see you do ``` task...

Ademord

### Description Adding `ai-traineree` to the Conda has been requested a few times. This should be a low hanging fruit to pull and might make a few people happy.

laszukdawid