---
license: unknown
---

# Intro

It's RL (Reinforcement Learning) PPO (Proximal Policy Optimization) model for DOOH DSP Bidder problem.
The model should respect 4 rules: 
- even pacing over time
- desired publishers distribution (which can be different from publishers distribution in raw bid requests flow).
- desired venue types distribution (which can be different from venue types distribution in raw bid requests flow).
- desired household sizes distribution (which can be different from household sizes 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_500_014_300_pt_distr_GOOD.png)

# Data flow

![alt](bidder_transormer_4_001.png)

# Python all-in-one files

- [dsp_bidder_4_training.py](https://huggingface.co/StanislavKo28/AdTech_DSP_Bidder___RL_PPO_4_rules/blob/main/p561_dsp_bidder_4_ppo_training.py) - training
- [dsp_bidder_4_environment.py](https://huggingface.co/StanislavKo28/AdTech_DSP_Bidder___RL_PPO_4_rules/blob/main/ppoenv/p561_dsp_bidder_4_ppo_environment_003_pt_distr_GOOD.py) - environment
- [dsp_bidder_4_inference.py](https://huggingface.co/StanislavKo28/AdTech_DSP_Bidder___RL_PPO_4_rules/blob/main/p591_dsp_bidder_4_ppo_inference.py) - inference
- [dsp_bidder_4_inference_once.py](https://huggingface.co/StanislavKo28/AdTech_DSP_Bidder___RL_PPO_4_rules/blob/main/p592_dsp_bidder_4_ppo_inference_once.py) - inference single bid request