Adamemento: Adaptive Memory-assisted Policy Optimization For Reinforcement Learning

Abstract

In sparse reward scenarios of reinforcement learning (RL), the memory mechanism provides promising shortcuts to policy optimization by reflecting on past experiences like humans. However, current memory-based RL methods simply store and reuse high-value policies, lacking a deeper refining and filtering of diverse past experiences and hence limiting the capability of memory. In this paper, we propose AdaMemento, an adaptive memory-enhanced RL framework. Instead of just memorizing positive past experiences, we design a memory-reflection module that exploits both positive and negative experiences by learning to predict known local optimal policies based on real-time states. To effectively gather informative trajectories for the memory, we further introduce a fine-grained intrinsic motivation paradigm, where nuances in similar states can be precisely distinguished to guide exploration. The exploitation of past experiences and exploration of new policies are then adaptively coordinated by e

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyyan2024adamemento

Related papers

• Re:frame -- Retrieving Experience From Associative Memory (2025)0.00
• Learning Self-imitating Diverse Policies (2018)0.00
• Memory Based Trajectory-conditioned Policies For Learning From Sparse Rewards (2019)0.00
• The Act Of Remembering: A Study In Partially Observable Reinforcement Learning (2020)0.00
• Regret-aware Policy Optimization: Environment-level Memory For Replay Suppression Under Delayed Harm (2026)0.00
• Stable Hadamard Memory: Revitalizing Memory-augmented Agents For Reinforcement Learning (2024)0.00
• Context Meta-reinforcement Learning Via Neuromodulation (2021)6.34
• HMRL: Hyper-meta Learning For Sparse Reward Reinforcement Learning Problem (2020)0.00