6 results found Sort:

MishaLaskin
rad MishaLaskin
72
400
unknown
15
RAD: Reinforcement Learning with Augmented Data
rl ppo rad sac data- mujoc codebase dm-control model-free off-policy deep-learning deep-q-network deep-q-learning deeplearning-ai soft-actor-critic data-augmentations deep-neural-networks reinforcement-learning deep-learning-algorithms deep-reinforcement-learning
Created 2020-04-09
23 commits to master branch, last one 3 years ago
denisyarats
drq denisyarats
50
398
mit
13
DrQ: Data regularized Q
rl drq gym sac pixel mujoco python control pytorch dm-control model-free off-policy actor-critic deep-learning soft-actor-crit data-augmentation reinforcement-learning deep-reinforcement-learning
Created 2020-04-29
14 commits to master branch, last one 2 years ago
pokaxpoka
sunrise pokaxpoka
29
117
unknown
6
SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning
rl sac mujoco rainbow codebase dm-control model-free off-policy deep-learning deep-q-network deep-q-learning soft-actor-critic deep-neural-networks reinforcement-learning deep-reinforcement-learning
Created 2020-07-02
7 commits to master branch, last one 3 years ago
denisyarats
exorl denisyarats
8
99
mit
3
ExORL: Exploratory Data for Offline Reinforcement Learning
mujoco python control pytorch datasets exporation model-free off-policy offline-rl unsupevised deep-learning reinforcement-learning
Created 2022-02-06
7 commits to main branch, last one 2 years ago
UniBwTAS
ccma UniBwTAS
5
92
bsd-3-clause
2
Curvature Corrected Moving Average: An accurate and model-free path smoothing algorithm.
ros kernel python robotics smoothing model-free data-driven easy-to-use curve-fitting moving-average path-smoothing kernel-smoothing accurate-smoothing path-interpolation curvature-corrected-moving-average
Created 2023-04-17
33 commits to master branch, last one about a month ago
lucidrains
SAC-pytorch lucidrains
1
27
mit
5
Implementation of Soft Actor Critic and some of its improvements in Pytorch
robotics model-free deep-learning reinforcement-learning artificial-intelligence
Created 2024-02-12
13 commits to main branch, last one 4 months ago