gptkbp:instance_of
|
gptkb:organization
|
gptkbp:analyzes
|
gptkb:matplotlib
|
gptkbp:based_on
|
Lunar Lander game
|
gptkbp:can_be_used_with
|
various RL algorithms
|
gptkbp:challenges
|
new learners
|
gptkbp:developed_by
|
gptkb:Open_AI
|
gptkbp:difficulty
|
gptkb:tank
|
gptkbp:emulation
|
gptkb:planet
|
gptkbp:exhibited_at
|
RL concepts
|
gptkbp:features
|
2 D physics engine
|
gptkbp:feedback
|
on landing performance
|
gptkbp:has_gameplay_element
|
discrete action space
|
gptkbp:has_goal
|
land the lunar module safely
|
https://www.w3.org/2000/01/rdf-schema#label
|
Lunar Lander-v2
|
gptkbp:includes
|
reward system
|
gptkbp:is_accessible_by
|
gptkb:API
|
gptkbp:is_available_on
|
gptkb:archive
open-source license
|
gptkbp:is_compatible_with
|
gptkb:Graphics_Processing_Unit
gptkb:Py_Torch
|
gptkbp:is_designed_for
|
reinforcement learning
|
gptkbp:is_documented_in
|
Git Hub README
Open AI Gym documentation
|
gptkbp:is_evaluated_by
|
performance metrics
|
gptkbp:is_implemented_in
|
gptkb:Library
|
gptkbp:is_integrated_with
|
gptkb:Jupyter_notebooks
|
gptkbp:is_part_of
|
gptkb:Open_AI_Gym's_Atari_collection
AI competitions
Open AI Gym environments
RL benchmarks
RL curriculum
|
gptkbp:is_popular_in
|
machine learning community
AI practitioners
|
gptkbp:is_supported_by
|
tutorials
community contributions
|
gptkbp:is_tested_for
|
gptkb:A3_C
gptkb:Dueling_DQN
gptkb:CQL
gptkb:DDPG
gptkb:DQN
gptkb:Rainbow_DQN
SAC
various hardware platforms
TRPO
PPO
IQN
C51
HER
PP O2
PP O3
SA C2
SA C3
|
gptkbp:is_used_for
|
training agents
agent evaluation
benchmarking RL algorithms
|
gptkbp:is_used_in
|
gptkb:academic_research
|
gptkbp:offers
|
training environment
|
gptkbp:part_of
|
gptkb:stadium
|
gptkbp:provides
|
continuous action space
|
gptkbp:requires
|
agent to control the lander
|
gptkbp:state
|
continuous state space
|
gptkbp:suitable_for
|
educational purposes
|
gptkbp:supports
|
gptkb:language
|
gptkbp:updates
|
by developers
|
gptkbp:used_in
|
gptkb:Research_Institute
|
gptkbp:bfsParent
|
gptkb:stadium
|
gptkbp:bfsLayer
|
3
|