Moreus
February 2, 2021, 2:03pm
1
I Made something similar to Gridword with Grid Sensor.
My Ml Agent learn really nice but when I try play from lasted brain my ML agent play much worse
change request form Fixed update script to Decision Requester but don’t make difference (only play nice while leaning)
Version information:
OS: windows 10
Unity 2020.1.9f1
ml-agents: 0.23.0,
ml-agents-envs: 0.23.0,
Communicator API: 1.3.0,
PyTorch: 1.7.0+cu110
Hey warfanel, your video isn’t playing.
Can you try running mlagents-learn with --inference, --time-scale=1, and --resume? If it plays poorly with that, it’s most likely that the game behaves differently at high time scales. If not, we’ll have to investigate further. Thanks!
Moreus
February 2, 2021, 7:34pm
3
I’m sorry video was private.
Now with “–inference, --time-scale=1, and --resume”
is still different while learning
now I have 150+ fps
Moreus
February 6, 2021, 9:36am
4
My project
Scene: “Scene Maze Game”
script:
using UnityEngine;
using Unity.MLAgents;
using Unity.MLAgents.Sensors;
using System.Collections.Generic;
using Unity.MLAgents.Actuators;
using System;
namespace Game.Maze
{
public struct Wall_position
{
public int x; public int z;
public Wall_position(int x, int z)
{
this.x = x;
this.z = z;
}
public override bool Equals(object obj)
This file has been truncated. show original