gptkbp:instance_of
|
gptkb:environment
|
gptkbp:action
|
discrete
move left
move right
|
gptkbp:available_in
|
Open AI Gym library
|
gptkbp:community
|
active
|
gptkbp:created_by
|
gptkb:Open_AI
|
gptkbp:difficulty
|
easy to moderate
|
gptkbp:difficulty_levels
|
beginner
|
gptkbp:environment_type
|
classic control
|
gptkbp:evaluates
|
average reward
|
gptkbp:goal
|
balance a pole on a cart
|
gptkbp:has_applications_in
|
educational purposes
robot control
simulation training
research experiments
algorithm testing
|
gptkbp:has_variants
|
gptkb:Cart_Pole-v0
gptkb:Cart_Pole-v2
|
https://www.w3.org/2000/01/rdf-schema#label
|
Cart Pole-v1
|
gptkbp:influenced_by
|
gptkb:strategy
gptkb:robotics
control theory
|
gptkbp:introduced_in
|
gptkb:2016
|
gptkbp:is_a_framework_for
|
gptkb:Tensor_Flow
gptkb:Keras
gptkb:Py_Torch
|
gptkbp:is_popular_among
|
gptkb:students
gptkb:researchers
|
gptkbp:is_similar_to
|
gptkb:Mountain_Car-v0
gptkb:Acrobot-v1
|
gptkbp:latest_version
|
v1
|
gptkbp:max_episode_steps
|
gptkb:500
|
gptkbp:mission
|
stabilize the pole
|
gptkbp:observation_space
|
continuous
|
gptkbp:part_of
|
gptkb:gymnasium
|
gptkbp:prize_pool
|
+1 for each time step the pole remains upright
|
gptkbp:render
|
visualizes the environment
|
gptkbp:requires
|
gptkb:Matplotlib
gptkb:Python
gptkb:Num_Py
|
gptkbp:reset
|
initializes the environment
|
gptkbp:simulation_speed
|
real-time
|
gptkbp:state
|
4-dimensional vector
cart position
cart velocity
pole angle
pole angular velocity
|
gptkbp:step
|
takes an action and returns the next state
|
gptkbp:supports
|
gptkb:Deep_Q-Networks
Q-learning
Policy Gradients
|
gptkbp:termination_condition
|
cart position exceeds threshold
pole angle exceeds threshold
|
gptkbp:tutorials
|
many online resources
|
gptkbp:type
|
reinforcement learning problem
|
gptkbp:used_in
|
machine learning research
|
gptkbp:used_in_competitions
|
AI competitions
|
gptkbp:used_in_courses
|
AI courses
reinforcement learning courses
|
gptkbp:bfsParent
|
gptkb:gymnasium
|
gptkbp:bfsLayer
|
4
|