Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).

Implementation of the Soft Actor Critic algorithm using Pytorch.

PyTorch application of reinforcement learning DQN algorithms in OpenAI Atari Pong game.

PyTorch application of reinforcement learning algorithm in OpenAI LunarLander - DDPG

PyTorch application of reinforcement learning Advanced Policy Gradient algorithms in OpenAI BipedalWalker- PPO

PyTorch application of reinforcement learning Policy Gradient algorithms in OpenAI Cartpole - REINFORCE, Actor-Critic, A2C, A3C

PyTorch application of reinforcement learning DDPG and PPO algorithms in Unity 3D-Ball