Pith. sign in

Spinning Up in Deep Reinforcement Learning

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

1 Pith paper citing it

fields

cs.LG 1

years

2025 1

verdicts

REJECT 1

representative citing papers

When Maximum Entropy Misleads Policy Optimization

cs.LG · 2025-06-05 · reject · novelty 6.0

Maximum entropy RL can be formally steered into arbitrary suboptimal policies at convergence by adding entropy trap states, while standard RL is unaffected.

citing papers explorer

Showing 1 of 1 citing paper.

  • When Maximum Entropy Misleads Policy Optimization cs.LG · 2025-06-05 · reject · none · ref 3

    Maximum entropy RL can be formally steered into arbitrary suboptimal policies at convergence by adding entropy trap states, while standard RL is unaffected.