Ryan Pégoud

[FEATURE] Implement self-play for two-player zero-sum games

2

Issue: #99 Description: Add self-play versions of DQN and PPO for two-player zero-sum games in [PGX](https://github.com/sotetsuk/pgx/tree/main) environments. Checklist: - [x] Determine how to keep the value estimation consistent (e.g. flip...

Description: Add self-play versions of DQN and PPO for two-player zero-sum games in [PGX](https://github.com/sotetsuk/pgx/tree/main) environments. Checklist: - [ ] Determine how to keep the value estimation consistent (e.g. flip the...

## What? Prototype for the documentation website. #83 Run locally using: ```bash pip install mkdocs-material mkdocs serve ```

[FEATURE] Create a documentation website

4

As I've been taking lots of notes while reading papers related to Rainbow, I thought I'd set up the documentation website and flesh it out gradually. I'll link a pull...

New features: * Parallel PZ wrapper for Lasertag * Selfplay Curriculum * PPO training script using selfplay on lasertag ```python class SelfPlay(Curriculum): def __init__(self, agent, device: str, store_agents_on_cpu: bool =...

Here's the current state of my work on `multi_car_racing` and Domain Randomization: ## Installation: * Running the script still requires Docker for now, I also copied the `multi_car_racing` repository for...