Open dfamil opened 4 years ago
Hi there are a couple of changes to get it tot work
done() --> EndEpisode(); public override float[] Heuristic() --> public override void Heuristic(float[] actionsOut) //return action
i have tried this with another example (https://www.immersivelimit.com/tutorials/reinforcement-learning-penguins-part-2-unity-ml-agents was updated to .0.16 from 0.14.0) this and the agent's just giggled back and forth.
It seems it takes a while for it to learn
Hi there are a couple of changes to get it tot work
done() --> EndEpisode(); public override float[] Heuristic() --> public override void Heuristic(float[] actionsOut) //return action
i have tried this with another example (https://www.immersivelimit.com/tutorials/reinforcement-learning-penguins-part-2-unity-ml-agents was updated to .0.16 from 0.14.0) this and the agent's just giggled back and forth.