Changelog v1.0.3-alpha-2

1. Updated the qtable storage format (previous qtable is not comaptible with this version)
2. Created a "risk taking" mechanism which greatly reduces training time by making actions taken during training more contextual based instead of random.
3. Added more environment triggers for the bot to look up it's training data, now it also reacts to dangerous enviornment around it, typically lava, places where it might fall off, or sculk blocks.
4. Created very detailed reward mechanisms for the bot during training for the best possible efficiency.
5. Fixed the previous blockscanning code, now replaced using a DLS algorithm for better optimization.

Upcoming changes.

1. Introduce goal based reinforcement learning(You give the bot a goal and it will try to learn based on how to best achieve the goal you give).
2. Switch to Deep-Q learning instead of traditonal q-learning (TLDR: use a neural network instead of a table)
3. Create custom movement code for the bot for precise movement instead of carpet's server sided movement code.
4. Give the bot a sense of it's surroundings in more detail (like how we can see blocks around us in game) so that it can take more precise decisions. Right now it has knowledge of what blocks are around it, but it doesn't know how those blocks are placed around it, in what order/shape. I intend to fix that.
5. Implement human consciousness level reasoning??? (to some degree maybe) (BIG MAYBE)

Some video footage :

mob related reflex actions

https://github.com/user-attachments/assets/1700e1ff-234a-456f-ab37-6dac754b3a94

environment reaction

https://github.com/user-attachments/assets/786527d3-d400-4acd-94f0-3ad433557239

What to do to setup this version before playing the game(assuming you are a returning user) :

1. Make sure you still have ollama installed.
2. In cmd or terminal type `ollama pull nomic-embed-text (if not already done).
3. Type `ollama pull llama3.2`
4. Type `ollama rm gemma2 (if you still have it installed)
5. Type `ollama rm llama2 (if you still have it installed)
6. If you have run the mod before go to your .minecraft folder, navigate to a folder called config, and delete a file called settings.json5

Then make sure you have turned on ollama server. After that launch the game.

Type /configMan in chat and select llama3.2 as the language model, then hit save and exit.

Then type /bot spawn <yourBotName> <training (for training mode, this mode won't connect to language model) and play (for normal usage)

Youtube tutorial video (coming soon)