Search Results for "agents"

FRODO is a Java platform to solve Distributed Constraint Satisfaction Problems (DisCSPs) and Optimization Problems (DCOPs). It provides implementations for a variety of algorithms, including DPOP (and its variants), ADOPT, SynchBB, DSA...

Gym by OpenAI is a toolkit for developing and comparing reinforcement learning algorithms. It supports teaching agents, everything from walking to playing games like Pong or Pinball. Open source interface to reinforce learning tasks. The gym library provides an easy-to-use suite of reinforcement learning tasks. Gym provides the environment, you provide the algorithm. You can write your agent using your existing numerical computation library, such as TensorFlow or Theano.

...The project collects popular approaches such as dynamic programming, Monte Carlo methods, temporal difference learning, Q-learning, SARSA, deep Q-networks, and policy gradient techniques, often demonstrated with Python and OpenAI Gym environments so users can experiment with agents learning in simulated tasks. For each algorithm category, the repository pairs conceptual descriptions with runnable code and often illustrated exercises that help solidify understanding by bridging theory with practice. It’s structured to serve learners progressing from basic tabular methods to function approximation and deep learning extensions, making it suitable for students, researchers, or practitioners exploring reinforcement learning fundamentals.

MADDPG (Multi-Agent Deep Deterministic Policy Gradient) is the official code release from OpenAI’s paper Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments. The repository implements a multi-agent reinforcement learning algorithm that extends DDPG to scenarios where multiple agents interact in shared environments. Each agent has its own policy, but training uses centralized critics conditioned on the observations and actions of all agents, enabling learning in cooperative, competitive, and mixed settings. The code is built on top of TensorFlow and integrates with the Multiagent Particle Environments (MPE) for benchmarking. ...