Pith. sign in

Magnetic control of tokamak plasmas through deep reinforcement learning

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

background 1

representative citing papers

Meta-learning how to Share Credit among Macro-Actions

cs.LG · 2025-06-16 · conditional · novelty 6.0

MASP meta-learns a similarity matrix over macro-actions and regularizes Q-values so that similar actions move together, improving exploration and performance in augmented-action-space RL.

citing papers explorer

Showing 1 of 1 citing paper.

  • Meta-learning how to Share Credit among Macro-Actions cs.LG · 2025-06-16 · conditional · none · ref 5

    MASP meta-learns a similarity matrix over macro-actions and regularizes Q-values so that similar actions move together, improving exploration and performance in augmented-action-space RL.