rl · GitHub Topics

google / dopamine

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

翻译 - 多巴胺是用于强化学习算法的快速原型制作的研究框架。

rl 机器学习人工智能 Google Tensorflow

Jupyter Notebook 10.66 k

4 个月前

thu-ml / tianshou

An elegant PyTorch deep reinforcement learning library.

翻译 - 优雅，灵活和超快的PyTorch深度强化学习平台。

PyTorch policy-gradient dqn double-dqn a2c ddpg ppo td3 sac imitation-learning mujoco atari rl cql

Python 8.27 k

13 小时前

junxiaosong / AlphaZero_Gomoku

An implementation of the AlphaZero algorithm for Gomoku (also called Gobang or Five in a Row)

alphazero mcts alphago-zero gobang monte-carlo-tree-search alphago reinforcement-learning rl board-game self-learning PyTorch Tensorflow

Python 3.44 k

1 年前

pytorch / ELF

ELF: a platform for game research with AlphaGoZero/AlphaZero reimplementation

翻译 - ELF：AlphaGoZero / AlphaZero重新实现的游戏研究平台

reinforcement-learning alphago-zero rl rl-environment alpha-zero Go

C++ 3.39 k

6 年前

werner-duvaud / muzero-general

#计算机科学#MuZero

翻译 - 零

muzero reinforcement-learning alphazero PyTorch Python self-learning monte-carlo-tree-search 深度学习 deep-reinforcement-learning 神经网络 rl tensorboard gym mcts alphago 机器学习

Python 2.6 k

6 个月前

pytorch / rl

#计算机科学#A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

人工智能 control decision-making distributed-computing 机器学习 marl model-based-reinforcement-learning multi-agent-reinforcement-learning PyTorch reinforcement-learning rl Robotics torch

Python 2.59 k

2 天前

IntelLabs / coach

#计算机科学#Reinforcement Learning Coach by Intel AI Lab enables easy experimentation with state of the art Reinforcement Learning algorithms

翻译 - 英特尔AI实验室的强化学习教练可轻松进行最新的强化学习算法实验

coach openai-gym reinforcement-learning Tensorflow rl carla imitation-learning mujoco roboschool 深度学习 starcraft starcraft2 mxnet onnx

Python 2.34 k

2 年前

DLR-RM / rl-baselines3-zoo

A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.

rl reinforcement-learning stable-baselines openai gym pybullet hyperparameter-optimization hyperparameter-tuning hyperparameter-search optimization sde Robotics lab deep-reinforcement-learning PyTorch

Python 2.28 k

7 天前

MaximeVandegar / Papers-in-100-Lines-of-Code

#计算机科学#Implementation of papers in 100 lines of code.

Python research 深度学习机器学习 educational PyTorch papers generative-model nerf 人工智能 gans aes 3D meta-learning neural-radiance-fields reinforcement-learning rl diffusion-models

Python 1.45 k

3 个月前

pathak22 / noreward-rl

#计算机科学#[ICML 2017] TensorFlow code for Curiosity-driven Exploration for Deep Reinforcement Learning

deep-reinforcement-learning exploration 深度学习 rl 深度神经网络 mario doom self-supervised Tensorflow openai-gym

Python 1.42 k

2 年前

araffin / rl-baselines-zoo

A collection of 100+ pre-trained RL agents using Stable Baselines, training and hyperparameter optimization included.

rl reinforcement-learning stable-baselines openai-gym openai gym pybullet optimization hyperparameter-optimization hyperparameter-search hyperparameter-tuning

Python 1.16 k

2 年前

MushroomRL / mushroom-rl

#计算机科学#Python library for Reinforcement Learning.

reinforcement-learning deep-reinforcement-learning 深度学习 openai-gym atari rl PyTorch mujoco dqn ddpg pybullet sac

Python 861

23 天前

google-research / rliable

#计算机科学#[NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.

reinforcement-learning benchmarking evaluation-metrics 机器学习 Google rl

Jupyter Notebook 808

7 个月前

google-research / seed_rl

SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference. Implements IMPALA and R2D2 algorithms in TF2 with SEED's architecture.

翻译 - SEED RL：具有加速的中央推理功能的可扩展，高效的Deep-RL。使用SEED的体系结构在TF2中实现IMPALA和R2D2算法。

rl impala r2d2 atari deepmind-lab google-research-football tf2 Google 云

Python 801

2 年前

zzli2022 / Awesome-System2-Reasoning-LLM

Latest Advances on System-2 Reasoning

benchmark mcts o1 prm reasoning rl

Python 685

2 天前

Toni-SM / skrl

#计算机科学#Modular reinforcement learning library (on PyTorch and JAX) with support for NVIDIA Isaac Gym, Omniverse Isaac Gym and Isaac Lab

reinforcement-learning Python openai-gym PyTorch 深度学习 deepmind gym isaac-sim rl 机器学习 Robotics jax

Python 673

10 天前

benedekrozemberczki / awesome-monte-carlo-tree-search-papers

#学习与技能提升#A curated list of Monte Carlo tree search papers with implementations.

tree-search learning 机器学习深度学习 monte-carlo-tree-search reinforcement-learning atari rl deep-q-learning q-learning reinforcement-learning-algorithms policy-gradient

Python 665

1 年前

utilForever / RosettaStone

Hearthstone simulator using C++ with some reinforcement learning

hearthstone reinforcement-learning C++hearthstone-api rl rl-environment python-api

C++ 664

9 个月前

araffin / rl-tutorial-jnrr19

Stable-Baselines tutorial for Journées Nationales de la Recherche en Robotique 2019

reinforcement-learning 教程 stable-baselines rl Python colab-notebook notebook

Jupyter Notebook 634

2 年前

ashishpatel26 / Real-time-ML-Project

#计算机科学#A curated list of applied machine learning and data science notebooks and libraries across different industries.

application 机器学习深度学习 real-time real-time-data dl rl Project Tensorflow Keras PyTorch theano

629

1 年前