Browsing by Subject "Reinforcement Learning"
Now showing items 1-3 of 3
-
A Comparison of Traversal Strategies for Tangled Program Graphs under the Arcade Learning Environment
(2021-04-27)Tangled program graphs provides a framework for constructing modular genetic programming solutions to visual reinforcement learning tasks. In order to guard against the development of cycles within the resulting graph, and ... -
ON DEVELOPMENTAL VARIATION IN HIERARCHICAL SYMBIOTIC POLICY SEARCH
(2012-08-27)A hierarchical symbiotic framework for policy search with genetic programming (GP) is evaluated in two control-style temporal sequence learning domains. The symbiotic formulation assumes each policy takes the form of a ... -
Reinforcement Learning with Real Valued Tangled Program Graphs
(2021-08-27)Tangled Program Graphs (TPG) represents a framework for evolving programs under an explicitly emergent model for modularity. The framework has been very successful at discovering solutions to tasks with delayed rewards ...