Maximum entropy RL can be formally steered into arbitrary suboptimal policies at convergence by adding entropy trap states, while standard RL is unaffected.
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 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
When Maximum Entropy Misleads Policy Optimization
Maximum entropy RL can be formally steered into arbitrary suboptimal policies at convergence by adding entropy trap states, while standard RL is unaffected.