Gymnasium
Gymnasium is a maintained fork of OpenAI’s Gym library, providing a standard API for reinforcement learning and a diverse collection of reference environments. The Gymnasium interface is simple, pythonic, and capable of representing general RL problems, and has a compatibility wrapper for old Gym environments. At the core of Gymnasium is the Env class, a high-level Python class representing a Markov Decision Process (MDP) from reinforcement learning theory. The class provides users the ability to generate an initial state, transition to new states given an action, and visualize the environment. Alongside Env, Wrapper classes are provided to help augment or modify the environment, particularly the agent observations, rewards, and actions taken. Gymnasium includes various built-in environments and utilities to simplify researchers’ work, along with being supported by most training libraries.
Learn more
TF-Agents
TensorFlow Agents (TF-Agents) is a comprehensive library designed for reinforcement learning in TensorFlow. It simplifies the design, implementation, and testing of new RL algorithms by providing well-tested modular components that can be modified and extended. TF-Agents enables fast code iteration with good test integration and benchmarking. It includes a variety of agents such as DQN, PPO, REINFORCE, SAC, and TD3, each with their respective networks and policies. It also offers tools for building custom environments, policies, and networks, facilitating the creation of complex RL pipelines. TF-Agents supports both Python and TensorFlow environments, allowing for flexibility in development and deployment. It is compatible with TensorFlow 2.x and provides tutorials and guides to help users get started with training agents on standard environments like CartPole.
Learn more
Qwen3-Coder
Qwen3‑Coder is an agentic code model available in multiple sizes, led by the 480B‑parameter Mixture‑of‑Experts variant (35B active) that natively supports 256K‑token contexts (extendable to 1M) and achieves state‑of‑the‑art results comparable to Claude Sonnet 4. Pre‑training on 7.5T tokens (70 % code) and synthetic data cleaned via Qwen2.5‑Coder optimized both coding proficiency and general abilities, while post‑training employs large‑scale, execution‑driven reinforcement learning, scaling test‑case generation for diverse coding challenges, and long‑horizon RL across 20,000 parallel environments to excel on multi‑turn software‑engineering benchmarks like SWE‑Bench Verified without test‑time scaling. Alongside the model, the open source Qwen Code CLI (forked from Gemini Code) unleashes Qwen3‑Coder in agentic workflows with customized prompts, function calling protocols, and seamless integration with Node.js, OpenAI SDKs, and environment variables.
Learn more
GLM-5
GLM-5 is Z.ai’s latest large language model built for complex systems engineering and long-horizon agentic tasks. It scales significantly beyond GLM-4.5, increasing total parameters and training data while integrating DeepSeek Sparse Attention to reduce deployment costs without sacrificing long-context capacity. The model combines enhanced pre-training with a new asynchronous reinforcement learning infrastructure called slime, improving training efficiency and post-training refinement. GLM-5 achieves best-in-class performance among open-source models across reasoning, coding, and agent benchmarks, narrowing the gap with leading frontier models. It ranks highly on evaluations such as Vending Bench 2, demonstrating strong long-term planning and operational capabilities. The model is open-sourced under the MIT License.
Learn more
