---
license: unknown
---

# Intro

It's RL (Reinforcement Learning) DQN (Deep Q-Learning) model for DOOH DSP Bidder problem.
The model should respect 2 rules: 
- even pacing over time
- desired publisher distribution (which can be different from publishers distribution in raw bid requests flow).

# Requirements.txt

```
torch==2.10.0
matplotlib==3.10.8
ipython==8.0.0
torchrl==0.11.1
tensordict==0.11.0
numpy==2.4.2
pandas==2.3.3
```

# Training process

![alt](training_200_035_250_GOOD_2.png)

# Data flow

![alt](bidder_transormer_2_012.png)

# Python all-in-one files

- [dsp_bidder_2_training.py](https://huggingface.co/StanislavKo28/DSP_Bidder_2_rules/blob/main/dsp_bidder_2_training.py) - training
- [dsp_bidder_2_inference.py](https://huggingface.co/StanislavKo28/DSP_Bidder_2_rules/blob/main/dsp_bidder_2_inference.py) - testing