# Reinforcement Learning Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/reinforcement-learning
> Markdown URL: https://aitinkerers.org/technologies/reinforcement-learning.md
> Technology record last updated: 2026-02-23T09:46:48Z
> Generated: 2026-09-21T04:44:25Z

Reinforcement Learning (RL) trains an autonomous agent to select optimal actions within an environment, maximizing its cumulative reward signal through continuous trial-and-error.

RL is a decision-making framework: an agent learns an optimal policy by interacting with a dynamic environment (modeled as a Markov Decision Process or MDP). The agent executes an action, receives a new state, and gets a scalar reward (positive or negative). This trial-and-error loop drives the agent to maximize the total long-term reward. This core mechanism enabled DeepMind's AlphaGo to master the game of Go and is critical for autonomous vehicles navigating complex traffic scenarios. Key algorithms like Q-Learning, Policy Gradients, and Actor-Critic methods define the agent's strategy for balancing exploration (trying new actions) and exploitation (using known high-reward actions).

- Official technology site: https://spinningup.openai.com/en/latest/index.html
- Public AI Tinkerers demos and talks: 6
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Teaching an LLM to Play Riftbound](https://ottawa.aitinkerers.org/talks/rsvp_CPcwK2QKRgg)

Samuel demonstrates a framework he built to teach AI agents to play Riftbound, the League of Legends-based trading card game. The system translates English card text and the current board state into legal actions, uses Gemma to choose moves in player-versus-bot or bot-versus-bot simulations, and is designed to generate training experience so a faster machine-learning policy can eventually select optimal plays without relying on slower LLM inference at the final decision stage.

- Event context: AI Tinkerers Ottawa Meetup - June 20th, 2026 — 2026-06-20 — Ottawa
- Public talk page: https://ottawa.aitinkerers.org/talks/rsvp_CPcwK2QKRgg

### [MakoraGenerate - AI Agent for Optimizing GPU Code](https://poland.aitinkerers.org/talks/rsvp_bSNP53ASxRc)

MakoraGenerate writes highly performant GPU kernels, low-level code that is the backbone of modern AI compute infrastructure.

- Event context: AI Tinkerers Poland - Meetup in Gdańsk #1 — 2026-04-23 — Poland
- Public talk page: https://poland.aitinkerers.org/talks/rsvp_bSNP53ASxRc

### [Training AI Like a Dog: What Behavioral Science Reveals About Model Alignment](https://chicago.aitinkerers.org/talks/rsvp_pdXZi3kLrDs)

A behavioral auditing and intervention system that runs alongside a language model in real time, detecting drift, entropy, and reward signal dysfunction while correcting for root cause rather than surface behavior. Built off-API on a local small model with no GPU using operant conditioning principles from high-stakes K9 training as the architectural foundation.

- Event context: AI Tinkerers Chicago: April Meetup ft OneTwoLoop — 2026-04-14 — Chicago
- Public talk page: https://chicago.aitinkerers.org/talks/rsvp_pdXZi3kLrDs

### [From scratch, single file implementation of a scaled-down version of MuZero for CartPole/Atari(WIP)](https://zurich.aitinkerers.org/talks/rsvp_hNEGEsBZehc)

I'm reimplementing reinforcement learning algorithms from scratch, most recently MuZero. I want to understand what comes after LLMs. Models learning purely from experience of interacting with the environment seem interesting, see for example David Silver's recent start-up announcement. I want to show that it is possible to reimplement core parts of these algorithms in a single file.

- Event context: AI Tinkerers Zurich April 9th — 2026-04-09 — Zürich
- Public talk page: https://zurich.aitinkerers.org/talks/rsvp_hNEGEsBZehc

### [TextArena](https://singapore.aitinkerers.org/talks/rsvp_GnJWYL5EEJg)

TextArena is an OpenAI Gym style environment with 57 text based games (single-player, two-player and multi-player) that allows for evaluation and RL based training of the game playing capabilities of language models.

- Event context: AI Tinkerers Singapore: 3rd Meetup - November 19th, 2024 — 2024-11-19 — Singapore
- Public talk page: https://singapore.aitinkerers.org/talks/rsvp_GnJWYL5EEJg

### [Enhancing Video Search: Exploring Embedding Techniques and Feedback-Driven Optimization](https://boston.aitinkerers.org/talks/rsvp_O_zCGa8Nsk8)

We will demonstrate two methods for video search: one using video embeddings and another employing a thumbs-up/thumbs-down feedback system. This presentation highlights how vector search embeddings can be dynamically adjusted based on user input through the thumbs-up/thumbs-down approach.

- Event context: AI Tinkerers September Meetup Sponsored by BasisTech — 2024-09-23 — Boston
- Public talk page: https://boston.aitinkerers.org/talks/rsvp_O_zCGa8Nsk8

## Related Technologies

- [LLM](https://aitinkerers.org/technologies/llm) ([Markdown](https://aitinkerers.org/technologies/llm.md)) — 123 public demos
- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [PyTorch](https://aitinkerers.org/technologies/pytorch) ([Markdown](https://aitinkerers.org/technologies/pytorch.md)) — 273 public demos
- [AI](https://aitinkerers.org/technologies/ai) ([Markdown](https://aitinkerers.org/technologies/ai.md)) — 55 public demos
- [API](https://aitinkerers.org/technologies/api) ([Markdown](https://aitinkerers.org/technologies/api.md)) — 19 public demos
- [Atari](https://aitinkerers.org/technologies/atari) ([Markdown](https://aitinkerers.org/technologies/atari.md)) — 1 public demo
- [CartPole](https://aitinkerers.org/technologies/cartpole) ([Markdown](https://aitinkerers.org/technologies/cartpole.md)) — 1 public demo
- [FastAPI](https://aitinkerers.org/technologies/fastapi) ([Markdown](https://aitinkerers.org/technologies/fastapi.md)) — 181 public demos
- [game-playing agents](https://aitinkerers.org/technologies/game-playing-agents) ([Markdown](https://aitinkerers.org/technologies/game-playing-agents.md)) — 1 public demo
- [Gemma](https://aitinkerers.org/technologies/gemma) ([Markdown](https://aitinkerers.org/technologies/gemma.md)) — 4 public demos
- [GPT-5](https://aitinkerers.org/technologies/gpt-5) ([Markdown](https://aitinkerers.org/technologies/gpt-5.md)) — 30 public demos
- [Language Models](https://aitinkerers.org/technologies/language-models) ([Markdown](https://aitinkerers.org/technologies/language-models.md)) — 4 public demos
- [Large Language Models](https://aitinkerers.org/technologies/large-language-models) ([Markdown](https://aitinkerers.org/technologies/large-language-models.md)) — 8 public demos
- [Machine Learning](https://aitinkerers.org/technologies/machine-learning) ([Markdown](https://aitinkerers.org/technologies/machine-learning.md)) — 20 public demos
- [ML](https://aitinkerers.org/technologies/ml) ([Markdown](https://aitinkerers.org/technologies/ml.md)) — 11 public demos
- [MuZero](https://aitinkerers.org/technologies/muzero) ([Markdown](https://aitinkerers.org/technologies/muzero.md)) — 1 public demo
- [OpenAI](https://aitinkerers.org/technologies/openai) ([Markdown](https://aitinkerers.org/technologies/openai.md)) — 112 public demos
- [OpenAI Gym](https://aitinkerers.org/technologies/openai-gym) ([Markdown](https://aitinkerers.org/technologies/openai-gym.md)) — 2 public demos