# Reinforcement learning training

MiMo is a series of 7B parameter models trained from scratch for inference tasks. Through optimized pre-training and post-training strategies, it performs excellently in mathematical and code reasoning tasks.

QwenLong-L1-32B is a large language model designed for long context reasoning. It is trained through reinforcement learning and performs excellently in multiple long context question answering benchmark tests, capable of effectively handling complex reasoning tasks.

Seed-Coder is an 8B-scale open-source code model family, including base, instruction, and reasoning versions. The reasoning version enhances reasoning capabilities through reinforcement learning training and supports 64K context length.

A 32-billion-parameter dense language model focused on enhancing reasoning capabilities, built upon Qwen 2.5-32B-Base, demonstrating performance comparable to larger MoE models in reasoning benchmarks.

DeepSeek-R1 is the first-generation inference model, which performs excellently in mathematics, code, and reasoning tasks, and its performance is comparable to that of OpenAI-o1.

This is a reinforcement learning model based on the DQN algorithm, specifically designed for the Atari game environment BeamRiderNoFrameskip-v4.

This is a deep reinforcement learning model based on the DQN algorithm, specifically designed for the Atari game environment BreakoutNoFrameskip-v4.

This is a Deep Q-Network (DQN) based reinforcement learning agent, specifically trained to play the Atari game 'Space Invaders'

This is a DQN reinforcement learning agent trained using the stable-baselines3 library, specifically designed to solve the Acrobot-v1 control problem.

This is a reinforcement learning model based on the DQN algorithm, specifically designed for the PongNoFrameskip-v4 environment.