# Reinforcement Learning Training

Thinkless is a large language model trained via reinforcement learning, capable of adaptively selecting short or long-chain reasoning modes, significantly reducing inference computational costs.

A 7B-parameter specialized inference language model series launched by Xiaomi, significantly enhancing mathematical and code reasoning capabilities through optimized pre-training and post-training strategies

MiMo-7B-RL is a reinforcement learning model trained based on the MiMo-7B-SFT model, achieving performance comparable to OpenAI o1-mini in mathematical and code reasoning tasks.

VL-Reasoner-7B is a multimodal reasoning model trained using GRPO-SSR technology, demonstrating outstanding performance across multiple multimodal reasoning benchmarks.

TimeZero is a reasoning-guided large-scale vision-language model (LVLM) specifically designed for temporal video grounding (TVG) tasks, achieving dynamic video-language relationship analysis through reinforcement learning methods.

TimeZero is a reasoning-guided large vision-language model (LVLM) specifically designed for temporal video grounding (TVG) tasks. It identifies temporal segments in videos corresponding to natural language queries through reinforcement learning methods.

The OpenChat v2 series is a language model based on the LLaMA-13B framework, trained with conditional weighted loss, surpassing ChatGPT performance in multiple benchmarks.

Promptist is a reinforcement learning-based automatic prompt optimization tool designed for Stable Diffusion, transforming user input into model-preferred prompts.

This is a reinforcement learning agent based on the DQN algorithm, specifically designed to play SpaceInvadersNoFrameskip-v4, trained using the stable-baselines3 library.

This is a reinforcement learning agent based on Deep Q-Network (DQN), specifically designed to solve tasks in the MountainCar-v0 environment.

This is a reinforcement learning agent based on Deep Q-Network (DQN), specifically trained to solve control problems in the MountainCar-v0 environment.

This is a DQN agent trained using the Stable Baselines3 library, specifically designed to play the SpaceInvadersNoFrameskip-v4 game.

This is a PPO agent model trained using the stable-baselines3 library, specifically designed for reinforcement learning tasks in the BipedalWalker-v3 environment.

This is a reinforcement learning model based on the PPO algorithm, specifically trained for the LunarLander-v2 environment to safely control the lunar lander.

This is a DQN agent trained using the stable-baselines3 library to solve reinforcement learning tasks in the LunarLander-v2 environment.

This is a reinforcement learning model based on the PPO algorithm, specifically designed to solve control problems in the Pendulum-v1 environment.

This is a PPO agent trained using the stable-baselines3 library, specifically designed to play the Atari game PongNoFrameskip-v4.