Reward Prediction Error Prioritisation In Experience Replay: The RPE-PER Method

Abstract

Reinforcement Learning algorithms aim to learn optimal control strategies through iterative interactions with an environment. A critical element in this process is the experience replay buffer, which stores past experiences, allowing the algorithm to learn from a diverse range of interactions rather than just the most recent ones. This buffer is especially essential in dynamic environments with limited experiences. However, efficiently selecting high-value experiences to accelerate training remains a challenge. Drawing inspiration from the role of reward prediction errors (RPEs) in biological systems, where they are essential for adaptive behaviour and learning, we introduce Reward Predictive Error Prioritised Experience Replay (RPE-PER). This novel approach prioritises experiences in the buffer based on RPEs. Our method employs a critic network, EMCN, that predicts rewards in addition to the Q-values produced by standard critic networks. The discrepancy between these predicted and act

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyyamani2025reward

Related papers

• Reward Prediction Error As An Exploration Objective In Deep RL (2019)2.26
• Improving Experience Replay With Successor Representation (2021)0.00
• Regret Minimization Experience Replay In Off-policy Reinforcement Learning (2021)0.00
• Prioritized Sequence Experience Replay (2019)0.00
• Introspective Experience Replay: Look Back When Surprised (2022)0.00
• Remember And Forget For Experience Replay (2018)0.00
• Replay For Safety (2021)0.00
• Large Batch Experience Replay (2021)0.00