Search Results for "actor"

...The project focuses on helping developers and researchers understand reinforcement learning methods by providing clean and reproducible implementations of well-known algorithms. It includes code for popular deep reinforcement learning techniques such as Deep Q-Networks, policy gradient methods, actor-critic architectures, and other modern RL approaches. The repository is structured so that users can easily experiment with different algorithms and training environments. Many examples demonstrate how agents learn to interact with simulated environments through trial and error using reinforcement learning principles. The codebase emphasizes clarity and modular design so that researchers can extend the implementations or use them for experimentation and benchmarking.

OAGI Python SDK is a Python client library for the Lux computer-use model that turns Lux into a programmable automation layer for operating human-facing software via vision and actions. It exposes the OAGI API in an ergonomic way, letting you trigger Lux in three main modes: Tasker for precise scripted sequences, Actor for fast one-shot tasks, and Thinker for open-ended, multi-step objectives. The SDK is designed around “computer use” as a paradigm, where the AI actually navigates interfaces, clicks, types, scrolls, and reads the screen through screenshots instead of only calling APIs. It provides high-level asynchronous agents (like AsyncDefaultAgent and AsyncActor) that encapsulate the loop of capturing screenshots, sending them to Lux, interpreting responses, and executing UI actions with PyAutoGUI. ...

rl_games is a high-performance reinforcement learning framework optimized for GPU-based training, particularly in environments like robotics and continuous control tasks. It supports advanced algorithms and is built with PyTorch.

LangGraph is a library for building stateful, multi-actor applications with LLMs, used to create agent and multi-agent workflows. Compared to other LLM frameworks, it offers these core benefits: cycles, controllability, and persistence. LangGraph allows you to define flows that involve cycles, essential for most agentic architectures, differentiating it from DAG-based solutions. As a very low-level framework, it provides fine-grained control over both the flow and state of your application, crucial for creating reliable agents. ...

...Each algorithm implementation is contained within a single file and typically ranges from about 100 to 150 lines of code, making it easy for learners to inspect the entire implementation at once. The repository includes examples of widely used reinforcement learning methods such as REINFORCE, Deep Q-Networks, Proximal Policy Optimization, and Actor-Critic architectures. Most experiments are designed to run quickly using the CartPole environment so that users can focus on understanding algorithm logic rather than computational infrastructure.

Multiagent Particle Environments is a lightweight framework for simulating multi-agent reinforcement learning tasks in a continuous observation space with discrete action settings. It was originally developed by OpenAI and used in the influential paper Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments. The environment provides simple particle-based worlds with simulated physics, where agents can move, communicate, and interact with each other. Scenarios are designed to model cooperative, competitive, and mixed interactions among agents, making it useful for testing algorithms in multi-agent settings. ...

Scalable Agent is the open implementation of IMPALA (Importance Weighted Actor-Learner Architectures), a highly scalable distributed reinforcement learning framework developed by Google DeepMind. IMPALA introduced a new paradigm for efficiently training agents across large-scale environments by decoupling acting and learning processes. In this architecture, multiple actor processes interact with their environments in parallel to collect trajectories, which are then asynchronously sent to a centralized learner for policy updates. ...

keras-rl implements some state-of-the-art deep reinforcement learning algorithms in Python and seamlessly integrates with the deep learning library Keras. Furthermore, keras-rl works with OpenAI Gym out of the box. This means that evaluating and playing around with different algorithms is easy. Of course, you can extend keras-rl according to your own needs. You can use built-in Keras callbacks and metrics or define your own. Even more so, it is easy to implement your own environments and...

...Its purpose is to serve as a baseline or reference implementation so researchers or developers can see how to build agents that operate in real-time, visual environments (e.g., games, browser apps) via pixel observations and keyboard/mouse actions. Under the hood, this starter agent implements a version of the A3C (Asynchronous Advantage Actor-Critic) algorithm, adapted for the specific challenges of Universe environments (e.g., network latency, VNC streaming, asynchronous observations). The repo includes modules like train.py, worker.py, model.py, a3c.py, and envs.py to support training, parallel worker management, policy/critics, and environment wrappers.