RPE-PER prioritises replay buffer samples by the absolute error between a learned reward model and the actual reward, and reports improved continuous-control RL performance in MuJoCo benchmarks.
Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Reward Prediction Error Prioritisation in Experience Replay: The RPE-PER Method
RPE-PER prioritises replay buffer samples by the absolute error between a learned reward model and the actual reward, and reports improved continuous-control RL performance in MuJoCo benchmarks.