BRRL derives an analytic optimal policy for regularized constrained RL that guarantees monotonic improvement and yields the BPO algorithm that matches or exceeds PPO.
Beyond the boundaries of proximal policy optimization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Bounded Ratio Reinforcement Learning
BRRL derives an analytic optimal policy for regularized constrained RL that guarantees monotonic improvement and yields the BPO algorithm that matches or exceeds PPO.