---
base_model: unsloth/mistral-7b-instruct-v0.3-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- trl
- openenv
- reinforcement-learning
- grpo
- agents
license: apache-2.0
language:
- en
thumbnail: https://huggingface.co/spaces/SParsh003/LifeOS-Personal-Chaos-Agen/resolve/main/docs/reward_curves.png
---

# 🧬 LifeOS Trained Agent (Mistral-7B-Instruct-v0.3)

![LifeOS Agent Banner](https://huggingface.co/spaces/SParsh003/LifeOS-Personal-Chaos-Agen/resolve/main/docs/Architecture.png)

This model was trained to survive the chaos of an unpredictable, stressful student week using **GRPO (Group Relative Policy Optimization)** within the [LifeOS OpenEnv](https://github.com/itzzSPcoder/LifeOS) simulation. 

It is a fine-tuned version of `mistralai/Mistral-7B-Instruct-v0.3` that has learned to balance multiple competing constraints—energy, stress, deadlines, social obligations, and budget—under conditions of high uncertainty (35% probability of random chaos events per step).

### 🏆 Meta OpenEnv Hackathon 2026 Submission

- **Live Demo (Interactive Space):** [SParsh003/LifeOS-Personal-Chaos-Agen](https://huggingface.co/spaces/SParsh003/LifeOS-Personal-Chaos-Agen)
- **Deep Dive Blog Post:** [Read the journey & methodology](https://huggingface.co/spaces/SParsh003/LifeOS-Personal-Chaos-Agen/blob/main/docs/hf_blog.md)
- **GitHub Repository:** [itzzSPcoder/LifeOS](https://github.com/itzzSPcoder/LifeOS)
- **Developed by:** Sparsh Bansal, Ayushika Verma, Aishani Mittal
- **License:** Apache 2.0

---

## 🚀 Model Capabilities: Triage over Grinding

Most agents fail at long-horizon personal planning because they treat scheduling as a static puzzle. This agent was trained in a dynamic environment where pushing too hard leads to burnout (-1.5 penalty) and ignoring friends leads to social debt (-0.8 penalty).

**Key Behaviors Learned via RL:**
1. **Proactive Recovery:** It learns to call the `rest` action *before* its energy drops to critical levels, avoiding burnout cascades.
2. **Social Debt Management:** It prioritizes the `reply_message` action to maintain relationships, clearing unread messages before they heavily penalize the social coherence score.
3. **Strategic Delegation:** It learns to use budget (₹) via `delegate_task` to offload low-priority work when energy is low and deadlines are looming.
4. **Resilience to Chaos:** When a random chaos event (e.g., "Deadline moved up by 2 days") fires, it can pause, recover, and pivot its focus without collapsing.

---

## 📊 Training Methodology

The model was trained entirely using Reinforcement Learning (GRPO) from the `trl` library, without human-labeled preference data. We designed a multi-objective reward function to prevent reward hacking:

1. **Task Completion:** +1.0 for finishing, -1.0 for missing deadlines.
2. **Social Coherence:** Penalty for leaving messages unread.
3. **Energy Sustainability:** +0.4 for proactive rest, -1.5 (Game Over) for burnout.
4. **Format Compliance:** Strict adherence to valid JSON actions.

**Training Stack:**
- **Frameworks:** `unsloth` (for 2x faster, memory-efficient 4-bit LoRA training), `trl` (GRPO Trainer).
- **Compute:** Single Google Colab T4 GPU (free tier).
- **Episodes:** 30 training episodes, 30 steps each.

![Reward Curves](https://huggingface.co/spaces/SParsh003/LifeOS-Personal-Chaos-Agen/resolve/main/docs/reward_curves.png)

---

## 💻 How to Use

This model is intended to be used as a policy agent within the **LifeOS OpenEnv framework**. It expects a highly structured observation prompt and is trained to output a specific JSON action schema preceded by an inner monologue block.

### Example Input (Observation):
```text
=== Step 14 / 30 ===
Vitals: Energy=35, Stress=72
Resources: Budget=₹1800, Relationships=0.60
Chaos Event: Assignment deadline moved up by 2 days!
Pending Tasks: 3
Unread Messages: 1
```

### Example Output (Agent Action):
```text
<thought>
Energy is at 35, which is dangerous territory. If I push to work on the urgent assignment now, I will hit 0 energy and burn out. I have enough budget to offload the minor task, but first I must rest to recover my vitals before tackling the big deadline.
</thought>
{
  "action_type": "rest",
  "reasoning": "Need to recover energy before prioritizing the urgent assignment."
}
```

---

## ⚙️ Loading the Model

You can load this model directly using Hugging Face `transformers` or `unsloth` for faster inference.

```python
from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name = "SParsh003/LifeOS-Trained-Agent",
    max_seq_length = 2048,
    dtype = None,
    load_in_4bit = True,
)

FastLanguageModel.for_inference(model)

prompt = """... (insert LifeOS observation here) ..."""
inputs = tokenizer([prompt], return_tensors="pt").to("cuda")

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

This model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) 🦥.