Life & fun · alternatives · 2026
24 alternatives to Beating Pokemon Red with RL and <10M Parameters
Hi everyone! After spending hundreds of hours, we're excited to finally share our progress in developing a reinforcement learning system to beat Pokémon Red. Our system successfully completes the game using a policy under 10M parameters, PPO, and a few novel techniques. With the release of Claude Plays Pokémon, now feels like the perfect time to showcase our work. We'd love to get feedback!
A reinforcement learning system that completes Pokémon Red using a policy under 10 million parameters and the PPO algorithm. The project demonstrates novel techniques for training game-playing AI agents on complex… Below are 24 products that do a similar job, ranked by how close each is in meaning and then by launch-day votes.
- 1
Watch the AI decision model Jev play Pokémon Red in its entirety, live.
28d ago · jev-pokemon.vercel.app · its alternatives →
- 2
In browser PPO training demo, made possible by tinygrad: TinyJit -> WebGPU kernels. Requires WebGPU.
May 2026 · ppo.gradexp.xyz · its alternatives →
- 3
A 60-second game about LLM permission fatigue. Claude Code needs your approval — but are you really reading the commands?
May 2026 · llmgame.scalex.dev · its alternatives →
- 4
Can a neural network predict your next move on a game of rock, paper and scissor? - victorqribeiro/jokenpo
2019 · github.com · its alternatives →
- 5
2024 · graphgame.sabrina.dev · its alternatives →
- 6
I built a bot that plays Pokémon FireRed. It can explore, battle, and respond to game events. Farthest I made it was Viridian Forest. I paused development a couple months ago, but given the launch of ClaudePlaysPokemon, decided to open source!
2025 · github.com · its alternatives →
- 7
Fabraix▲196We built Adversarial Cost to Exploit (ACE), a benchmark that measures the token expenditure an autonomous adversary must invest to breach an LLM agent. Instead of binary pass/fail, ACE quantifies adversarial effort in dollars, enabling game-theoretic analysis of when an attack is economically rational. We tested six budget-tier models (Gemini Flash-Lite, DeepSeek v3.2, Mistral Small 4, Grok 4.1 Fast, GPT-5.4 Nano, Claude Haiku 4.5) with identical agent configs and an autonomous red-teaming attacker. Haiku 4.5 was an order of magnitude harder to break than every other model; $10.21 mean…
May 2026 · fabraix.com · its alternatives →
- 8
RL-training an AI agent to RL-train AI agents. Contribute to Danau5tin/ai-trains-ai development by creating an account on GitHub.
Jul 2026 · github.com · its alternatives →
- 9
- 10
Comprehensive toolkit for Reinforcement Learning from Human Feedback (RLHF) training, featuring instruction fine-tuning, reward model training, and support for PPO and DPO algorithms with various configurations for the Transformer 5 models including Qwen 3.0 - raghavc/LLM-RLHF-Tuning-with-PPO-and-DP
2024 · github.com · its alternatives →
- 11
A chess engine implementation inspired by AlphaZero, using MLX for neural network computations and Monte Carlo Tree Search (MCTS) for move selection.
2025 · github.com · its alternatives →
- 12
2015 · otoro.net · its alternatives →
- 13
I worked on this applied Deep Reinforcement Learning course for the better part of 2021. I made a Datacamp course [0] before, and this served as my inspiration to make an applied Deep RL series. Normally, Deep RL courses teach a lot of mathematically involved theory. You get the practical applications near the end (if at all). I have tried to turn that on its head. In the top-down approach, you learn practical skills first, then go deeper later. This is much more fun. This course (the first in a planned multi-part series) shows how to use the Deep Reinforcement Learning framework RLlib to…
2022 · courses.dibya.online · its alternatives →
- 14
A final project for Advanced Machine Learning. Build bots to play against this Tetris Sandbox! - mbrenman/TetrisPlayground
2015 · github.com · its alternatives →
- 15
- 16
"Creatures" is a stretch given that the environment is Minecraft, but the idea is simple: iteratively add blocks conditionally (tensor convolution) on the current environment (blocks) to maximize some reward. In this case I use PPO RL to train creatures to touch a glowstone block but you can adapt it to use any algorithm and reward (easily, as it uses the Ray framework). What I like about this work: iteratively finding solutions has a long and colorful history of doing things well: gradient boosting, ResNets, Stable Diffusion, etc. We're after some end optimal state and usually try to get…
2024 · github.com · its alternatives →
- 17
Hi! I build an MCP server that allows clients to play Minesweeper. It turns out that Claude is not very good at it (makes obvious mistakes, hasn't won a single game on a 9x9 board after many attempts). I am curious how I can prompt Claude to do better?
2025 · github.com · its alternatives →
- 18
After training calculator agent via RL, I really wanted to go bigger! So I built RL infrastructure for training long-horizon terminal/coding agents that scales from 2x A100s to 32x H100s (~$1M worth of compute!) Without any training, my 32B agent hit #19 on Terminal-Bench leaderboard, beating Stanford's Terminus-Qwen3-235B-A22! With training... well, too expensive, but I bet the results would be good! *What I did*: - Created a Claude Code-inspired agent (system msg + tools) - Built Docker-isolated GRPO training where each rollout gets its own container - Developed a multi-agent…
2025 · github.com · its alternatives →
- 19
Arc enables continual learning for agents to adapt, learn, and transfer knowledge in live environments. Open-source SDK for building agents that learn from experience and improve over time.
2025 · arc.computer · its alternatives →
- 20
2016 · blog.otoro.net · its alternatives →
- 21
On Pokemon Go & its impact to Nintendo
2016 · blcw.me · its alternatives →
- 22
We're excited to announce that we've open-sourced LeanRL, a lightweight PyTorch reinforcement learning library that provides recipes for fast RL training using torch.compile and CUDA graphs. By leveraging these tools, we've achieved significant speed-ups compared to the original CleanRL implementations - up to 6x faster! Reinforcement learning is notoriously CPU-bound due to the high frequency of small CPU operations. PyTorch's powerful compiler can help alleviate these issues, but comes with its own costs. LeanRL addresses this challenge by providing simple recipes to accelerate your…
2024 · github.com · its alternatives →
- 23PG
Christopher Clark Homepage
2015 · chrisc36.github.io · its alternatives →
- 24
Unity C# Flappy Bird + Neuroevolution. WebGl demo: http://nfb.gametroleum.com - KrzysztofBogdan/CsNeuroevolutionFlappyBird
2017 · github.com · its alternatives →
Also compare
- Jev Plays Pokémon Red alternatives
- Watch a neural net learn to play Snake alternatives
- Continue? Y/N: A 60-second game about AI agent permission fatigue alternatives
- Play rock paper and scissors against a untrained neural network alternatives
- I built a game to help you learn neural network architectures alternatives
- LLM plays Pokémon (open sourced) alternatives
Ranked by how close each launch is in meaning, then by votes. Prices were read from each product’s own site when checked and can change. Refine with your own description →