|
gptkbp:instance_of
|
gptkb:stadium
|
|
gptkbp:bfsLayer
|
4
|
|
gptkbp:bfsParent
|
gptkb:Cart_Pole-v1
gptkb:Mountain_Car-v0
|
|
gptkbp:accessibility
|
Open-source.
|
|
gptkbp:activities
|
Discrete
Based on policy.
|
|
gptkbp:agent
|
High.
Various.
Easy.
Varies.
Critical.
Essential.
Necessary.
Periodic.
Iterative.
Policy Gradient.
Reward.
Steep.
|
|
gptkbp:analyzes
|
Available.
|
|
gptkbp:application
|
Yes.
|
|
gptkbp:can_be
|
Available.
|
|
gptkbp:character
|
Discrete actions.
|
|
gptkbp:code
|
Available on Git Hub.
|
|
gptkbp:collection_size
|
4.
|
|
gptkbp:community_support
|
Strong.
|
|
gptkbp:contribution
|
Active.
|
|
gptkbp:created_by
|
gptkb:Open_AI
|
|
gptkbp:dependency
|
Num Py.
|
|
gptkbp:difficulty
|
Easy
Beginner.
|
|
gptkbp:ends_at
|
Pole angle exceeds 15 degrees.
|
|
gptkbp:environment
|
gptkb:military_base
High.
Low.
Regular.
Present.
Comprehensive.
Simple.
Balancing.
Cart Pole-v0.
Mountain Car-v0.
Random.
Reinforcement Learning experiments.
Simple dynamics.
|
|
gptkbp:feedback
|
Positive.
Reward system.
|
|
gptkbp:focuses_on
|
Yes.
|
|
gptkbp:function
|
Simple.
|
|
gptkbp:game_length
|
2.
|
|
gptkbp:goal
|
Keep the pole balanced for as long as possible.
|
|
gptkbp:government_type
|
Stochastic.
|
|
gptkbp:has_method
|
Reset to a random state.
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Cart Pole-v0
|
|
gptkbp:is_analyzed_in
|
gptkb:software_framework
|
|
gptkbp:is_available_in
|
gptkb:stadium
|
|
gptkbp:is_described_as
|
A classic control problem where a pole is balanced on a cart.
|
|
gptkbp:is_evaluated_by
|
Average reward.
|
|
gptkbp:is_explored_in
|
Epsilon-greedy.
|
|
gptkbp:is_implemented_in
|
Python.
Numerous.
|
|
gptkbp:is_motivated_by
|
Not used.
|
|
gptkbp:is_observed_in
|
Continuous
|
|
gptkbp:is_scalable
|
Limited.
|
|
gptkbp:latest_version
|
0.1.0
|
|
gptkbp:library
|
Gym.
|
|
gptkbp:maintenance
|
Active.
|
|
gptkbp:number_of_episodes
|
gptkb:television_series
|
|
gptkbp:performance
|
Varies by agent.
|
|
gptkbp:pole_position
|
Continuous.
0.5 meters.
|
|
gptkbp:position
|
Continuous.
|
|
gptkbp:prize_money
|
1 for every timestep the pole remains upright.
|
|
gptkbp:release_date
|
gptkb:2016
|
|
gptkbp:risk_factor
|
Varies.
|
|
gptkbp:speed
|
Continuous.
Real-time.
|
|
gptkbp:state
|
Yes.
4-dimensional vector.
Deterministic.
Randomly generated.
Vector.
|
|
gptkbp:suitable_for
|
Newcomers to RL.
|
|
gptkbp:training
|
Varies.
Q-learning.
Varies by algorithm.
|
|
gptkbp:tutorials
|
Yes.
|
|
gptkbp:updates
|
Regular.
|
|
gptkbp:user_base
|
Large.
|
|
gptkbp:user_interface
|
Command line.
|