Can intelligent agents play Minecraft? Developing a hierarchical reinforcement learning agent to play Minecraft.
Note:
This study is a collaborative project between Max Planck Institute (Germany) and Dr. Shihan Wang (Utrecht University). and it is under supervision of Dr. Shihan Wang.
a. Assigning subtask for human-player.
b. Subtask could be the chain in HDQfD or Markov-controller or hand-crafted chain.
c. Potential research: Comparing Human-player performance between different provided chains.
a. Assigning action in the subtask for human-player.
b. For action, things might be a bit complex.
c. 10 basic actions:
Move -- [forward, back, left, right]
Camera -- [up, down, left, right]
Combo -- [forward+jump]
Attack
d. Special actions:
Craft -- [Planke, stick, crafting_table, wooden_pickaxe, etc]: converting raw material
Place -- [item]: placing item(s)
NearbyCraft -- [item]: Craft item(s) when something nearby
Equip -- [item]
The MineRL intelligent agent is based on HDQfD (forgER) algorithm, see [Paper] [Github].
Notes:
- We cannot reproduce the results in the paper, could be caused by multiple reasons, e.g: 1.dataset; 2.Bugs;
- We changed some parts of the algorithm to improve the performance.
- You will find more detals in the forger folder.
In order to find out how subtask state transitions are transfered, we implemented a Markov Model to analyze them. We first split the whole IronPickaxe dataset to different subtasks, e.g: Start, Log, Planks, Crafting tables etc, to extract the subtasks. After that, to keep consistency, we filtered some poor quality trajectories. Finally, the most greedy subtask path was generated by our Markov model..