Sample-efficient Reinforcement Learning With Maximum Entropy Mellowmax Episodic Control

Abstract

Deep networks have enabled reinforcement learning to scale to more complex and challenging domains, but these methods typically require large quantities of training data. An alternative is to use sample-efficient episodic control methods: neuro-inspired algorithms which use non-/semi-parametric models that predict values based on storing and retrieving previously experienced transitions. One way to further improve the sample efficiency of these approaches is to use more principled exploration strategies. In this work, we therefore propose maximum entropy mellowmax episodic control (MEMEC), which samples actions according to a Boltzmann policy with a state-dependent temperature. We demonstrate that MEMEC outperforms other uncertainty- and softmax-based exploration methods on classic reinforcement learning environments and Atari games, achieving both more rapid learning and higher final rewards.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysarrico2019sample

Related papers

• Sample Efficient Reinforcement Learning Via Model-ensemble Exploration And Exploitation (2021)0.00
• Memory-efficient Episodic Control Reinforcement Learning With Dynamic Online K-means (2019)0.00
• Continuous Episodic Control (2022)2.26
• Soft Actor-critic: Off-policy Maximum Entropy Deep Reinforcement Learning With A Stochastic Actor (2018)0.00
• Episodic Reinforcement Learning With Expanded State-reward Space (2024)0.00
• Maximum Entropy Diverse Exploration: Disentangling Maximum Entropy Reinforcement Learning (2019)0.00
• Towards Sample-efficient Episodic Control With DAC-ML (2020)0.00
• Sequential Memory Improves Sample And Memory Efficiency In Episodic Control (2021)0.00