High-Dimensional Continuous Control Using Generalized Advantage Estimation
URI: https://gptkb.org/entity/High-Dimensional_Continuous_Control_Using_Generalized_Advantage_Estimation
GPTKB entity
Statements (62)
| Predicate | Object |
|---|---|
| gptkbp:instance_of |
gptkb:academic_journals
|
| gptkbp:analysis |
statistical methods
|
| gptkbp:application |
gptkb:robotics
|
| gptkbp:author |
gptkb:unknown
|
| gptkbp:benefits |
generalized advantage
|
| gptkbp:challenge_addressed |
sample inefficiency
|
| gptkbp:challenges |
high-dimensional state spaces
|
| gptkbp:collaboration |
interdisciplinary teams
academic-industry partnerships |
| gptkbp:community |
gptkb:scientific_community
|
| gptkbp:community_impact |
technology advancement
|
| gptkbp:community_outreach |
workshops
|
| gptkbp:concluded_on |
promising results
|
| gptkbp:conference |
AI conferences
|
| gptkbp:contribution |
improving sample efficiency
|
| gptkbp:economic_impact |
automation
|
| gptkbp:evaluates |
sample efficiency
benchmark environments |
| gptkbp:field |
gptkb:Artificial_Intelligence
gptkb:machine_learning |
| gptkbp:focus |
continuous control tasks
|
| gptkbp:funding |
grants
|
| gptkbp:future_prospects |
real-world applications
scalability issues generalization capabilities |
| gptkbp:goal |
efficient learning
|
| gptkbp:has_programs |
gptkb:Tensor_Flow
gptkb:Py_Torch actor-critic |
| https://www.w3.org/2000/01/rdf-schema#label |
High-Dimensional Continuous Control Using Generalized Advantage Estimation
|
| gptkbp:impact |
high
deep reinforcement learning |
| gptkbp:is_a_framework_for |
policy optimization
|
| gptkbp:is_cited_in |
other research papers
|
| gptkbp:is_compared_to |
traditional methods
|
| gptkbp:is_considered |
cross-validation
|
| gptkbp:is_implemented_in |
open-source
|
| gptkbp:is_reviewed_by |
peers
|
| gptkbp:key_concept |
exploration-exploitation trade-off
|
| gptkbp:keywords |
deep learning
|
| gptkbp:methodology_type |
quantitative research
|
| gptkbp:notable_work |
robust performance
|
| gptkbp:orbital_period |
hyperparameters
|
| gptkbp:outcome |
improved stability
|
| gptkbp:performance |
cumulative reward
|
| gptkbp:provides_information_on |
simulated environments
synthetic data |
| gptkbp:published_in |
gptkb:unknown
|
| gptkbp:related_to |
policy gradient methods
|
| gptkbp:research |
experimental setup
|
| gptkbp:research_areas |
control theory
|
| gptkbp:result |
superior performance
|
| gptkbp:reviews |
literature on reinforcement learning
|
| gptkbp:significance |
advancement in control tasks
|
| gptkbp:technique |
Generalized Advantage Estimation
advantage function estimation |
| gptkbp:theory |
temporal difference learning
|
| gptkbp:topics |
reinforcement learning
|
| gptkbp:type |
empirical study
|
| gptkbp:year |
gptkb:unknown
|
| gptkbp:bfsParent |
gptkb:John_Schulman
|
| gptkbp:bfsLayer |
5
|