Open The Black Box: Step-based Policy Updates For Temporally-correlated Episodic Reinforcement Learning

Abstract

Current advancements in reinforcement learning (RL) have predominantly focused on learning step-based policies that generate actions for each perceived state. While these methods efficiently leverage step information from environmental interaction, they often ignore the temporal correlation between actions, resulting in inefficient exploration and unsmooth trajectories that are challenging to implement on real hardware. Episodic RL (ERL) seeks to overcome these challenges by exploring in parameters space that capture the correlation of actions. However, these approaches typically compromise data efficiency, as they treat trajectories as opaque *black boxes*. In this work, we introduce a novel ERL algorithm, Temporally-Correlated Episodic RL (TCE), which effectively utilizes step information in episodic policy updates, opening the 'black box' in existing ERL methods while retaining the smooth and consistent exploration in parameter space. TCE synergistically combines the advantages of s

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyli2024open

Related papers

• TOP-ERL: Transformer-based Off-policy Episodic Reinforcement Learning (2024)0.00
• Episodic Reinforcement Learning With Expanded State-reward Space (2024)0.00
• Explainable Reinforcement Learning Via Temporal Policy Decomposition (2025)0.00
• Evolution-guided Policy Gradient In Reinforcement Learning (2018)0.00
• Learning Self-imitating Diverse Policies (2018)0.00
• Exploration Via Elliptical Episodic Bonuses (2022)3.58
• Erl-re\(^2\): Efficient Evolutionary Reinforcement Learning With Shared State Representation And Individual Policy Representation (2022)0.00
• Collaborative Evolutionary Reinforcement Learning (2019)0.00