Top 19 sac open source projects

An elegant PyTorch deep reinforcement learning library.

✭ 4,109

python Makefile pytorch dqn ppo policy-gradient imitation-learning ddpg mujoco benchmark library rl cql atari sac drl npg double-dqn trpo a2c td3 bcq

Minimalrl

Implementations of basic RL algorithms with minimal lines of codes! (pytorch based)

✭ 2,051

python deep-learning machine-learning pytorch reinforcement-learning deep-reinforcement-learning simple dqn ppo a3c ddpg reinforce sac acer a2c policy-gradients

Meta-SAC

Auto-tune the Entropy Temperature of Soft Actor-Critic via Metagradient - 7th ICML AutoML workshop 2020

✭ 19

python deep-reinforcement-learning pytorch hyperparameter-optimization sac automl mujoco meta-learning soft-actor-critic

learning-to-drive-in-5-minutes

Implementation of reinforcement learning approach to make a car learn to drive smoothly in minutes

✭ 227

python simulator reinforcement-learning unity openai gym vae self-driving-car rl sac srl donkey-car state-representation-learning stable-baselines soft-actor-critic

TF2-RL

Reinforcement learning algorithms implemented for Tensorflow 2.0+ [DQN, DDPG, AE-DDPG, SAC, PPO, Primal-Dual DDPG]

✭ 160

python reinforcement-learning openai-gym dqn tensorboard ddpg sac ppo tensorflow2 ae-ddpg

ReinforcementLearningZoo.jl

juliareinforcementlearning.org/

✭ 46

julia machine-learning reinforcement-learning julia-language rainbow dqn hacktoberfest ddpg sac c51 cfr iqn ppo a2c td3 counterfactual-regret-minimization

Seismic-Data-Preparation

Preprocessing seismic data: download, format changing, and archiving

✭ 15

python shell seed obspy preprocess raw-data miniseed sac seismic-data reftek

Paddle-RLBooks

Paddle-RLBooks is a reinforcement learning code study guide based on pure PaddlePaddle.

ElegantRL

Scalable and Elastic Deep Reinforcement Learning Using PyTorch. Please star. 🔥

✭ 2,074

python Jupyter Notebook lightweight reinforcement-learning gae efficient pytorch stable dqn ddpg sac per multiple-gpu ppo a2c td3 model-free-rl drl-pytorch bipedalwalkerhardcore

model-free-algorithms

TD3, SAC, IQN, Rainbow, PPO, Ape-X and etc. in TF1.x

✭ 56

python reinforcement-learning rainbow ddpg sac ppo td3 model-free-rl

proto

Proto-RL: Reinforcement Learning with Prototypical Representations

✭ 67

python control reinforcement-learning deep-learning pixel pytorch gym rl representation-learning unsupervised-learning proto sac mujoco dm-control soft-actor-critic drq proto-rl unsupervised-rl

LWDRLC

Lightweight deep RL Libraray for continuous control.

✭ 14

python shell Dockerfile deep-reinforcement-learning pytorch policy-gradient ddpg sac continuous-control ppo td3

pomdp-baselines

Simple (but often Strong) Baselines for POMDPs in PyTorch - ICML 2022

✭ 162

python Jupyter Notebook shell deep-reinforcement-learning pytorch recurrent-neural-networks sac pomdp generalization credit-assignment meta-rl robust-rl td3 discrete-sac

jax-rl

JAX implementations of core Deep RL algorithms

✭ 61

python Makefile reinforcement-learning deep-learning deep-reinforcement-learning flax deepmind mpo sac actor-critic maximum-a-posteriori-estimation mujoco jax td3 soft-actor-critic

Rainy

☔ Deep RL agents with PyTorch☔

✭ 39

python Makefile reinforcement-learning deep-reinforcement-learning pytorch dqn ddpg sac ppo a2c acktr option-critic td3

PH5

Library of PH5 clients, apis, and utilities

✭ 14

python c shell science seismology hdf5 miniseed hdf5-format sac ph5 seg-y

Deep-Reinforcement-Learning-With-Python

Master classic RL, deep RL, distributional RL, inverse RL, and more using OpenAI Gym and TensorFlow with extensive Math

omd

JAX code for the paper "Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation"

✭ 43

Jupyter Notebook python machine-learning reinforcement-learning deep-learning automatic-differentiation deep-reinforcement-learning dqn gym flax haiku sac model-based-rl jax model-based-reinforcement-learning soft-actor-critic dm-haiku

mujoco-benchmark

Provide full reinforcement learning benchmark on mujoco environments, including ddpg, sac, td3, pg, a2c, ppo, library

✭ 101

benchmark performance pytorch rl baseline results ddpg sac drl mujoco ppo tianshou

1-19 of 19 sac projects