|
gptkbp:instanceOf
|
gptkb:open-source_library
|
|
gptkbp:category
|
gptkb:model
reinforcement learning framework
|
|
gptkbp:compatibleWith
|
gptkb:OpenAI_Gym
gptkb:PettingZoo
gptkb:RLlibEnv
gptkb:Unity_ML-Agents
|
|
gptkbp:developedBy
|
gptkb:Ray_Project
|
|
gptkbp:documentation
|
https://docs.ray.io/en/latest/rllib/index.html
|
|
gptkbp:firstReleased
|
2018
|
|
gptkbp:integratesWith
|
gptkb:TensorFlow
gptkb:PyTorch
gptkb:Ray_Serve
gptkb:Ray_Tune
|
|
gptkbp:license
|
Apache 2.0
|
|
gptkbp:partOf
|
gptkb:right
|
|
gptkbp:programmingLanguage
|
gptkb:Python
|
|
gptkbp:repository
|
https://github.com/ray-project/ray
|
|
gptkbp:supports
|
hyperparameter tuning
cloud deployment
multi-agent reinforcement learning
custom environments
scalable training
model-based RL
offline RL
|
|
gptkbp:supportsAlgorithm
|
gptkb:ES
gptkb:A3C
gptkb:DQN
gptkb:APEX
gptkb:IMPALA
gptkb:SAC
PPO
MARL
|
|
gptkbp:usedFor
|
gptkb:reinforcement_learning
deep learning
distributed training
|
|
gptkbp:bfsParent
|
gptkb:AI2-THOR
|
|
gptkbp:bfsLayer
|
6
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
RLlib
|