Safe And Robust Experience Sharing For Deterministic Policy Gradient Algorithms

Abstract

Learning in high dimensional continuous tasks is challenging, mainly when the experience replay memory is very limited. We introduce a simple yet effective experience sharing mechanism for deterministic policies in continuous action domains for the future off-policy deep reinforcement learning applications in which the allocated memory for the experience replay buffer is limited. To overcome the extrapolation error induced by learning from other agents' experiences, we facilitate our algorithm with a novel off-policy correction technique without any action probability estimates. We test the effectiveness of our method in challenging OpenAI Gym continuous control tasks and conclude that it can achieve a safe experience sharing across multiple agents and exhibits a robust performance when the replay memory is strictly limited.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysaglam2022safe

Related papers

• Off-policy Correction For Deep Deterministic Policy Gradient Algorithms Via Batch Prioritized Experience Replay (2021)0.00
• CUER: Corrected Uniform Experience Replay For Off-policy Continuous Deep Reinforcement Learning Algorithms (2024)0.00
• Adaptive Experience Selection For Policy Gradient (2020)0.00
• On The Convergence Of Experience Replay In Policy Optimization: Characterizing Bias, Variance, And Finite-time Convergence (2021)0.00
• Parameter Sharing Deep Deterministic Policy Gradient For Cooperative Multi-agent Reinforcement Learning (2017)0.00
• Replay For Safety (2021)0.00
• Asynchronous Episodic Deep Deterministic Policy Gradient: Towards Continuous Control In Computationally Complex Environments (2019)0.00
• Experience Augmentation: Boosting And Accelerating Off-policy Multi-agent Reinforcement Learning (2020)0.00