Deep RL with action decomposition and reward shifting learns a symbolic multi-parameter policy for (1+(λ,λ))-GA on OneMax that outperforms baselines across problem sizes.
Challenges to solving combinatorially hard long-horizon deep RL tasks,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Discovering Interpretable Multi-Parameter Control Policies for Evolutionary Algorithms Using Deep Reinforcement Learning
Deep RL with action decomposition and reward shifting learns a symbolic multi-parameter policy for (1+(λ,λ))-GA on OneMax that outperforms baselines across problem sizes.