Reproducibility Of Benchmarked Deep Reinforcement Learning Tasks For Continuous Control

Abstract

Policy gradient methods in reinforcement learning have become increasingly prevalent for state-of-the-art performance in continuous control tasks. Novel methods typically benchmark against a few key algorithms such as deep deterministic policy gradients and trust region policy optimization. As such, it is important to present and use consistent baselines experiments. However, this can be difficult due to general variance in the algorithms, hyper-parameter tuning, and environment stochasticity. We investigate and discuss: the significance of hyper-parameters in policy gradients for continuous control, general variance in the algorithms, and reproducibility of reported results. We provide guidelines on reporting novel results as comparisons against baseline methods such that future researchers can make informed decisions when investigating novel methods.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyislam2017reproducibility

Related papers

• The Definitive Guide To Policy Gradients In Deep Reinforcement Learning: Theory, Algorithms And Implementations (2024)3.29
• Comparing Deep Reinforcement Learning And Evolutionary Methods In Continuous Control (2017)0.00
• Learning Optimal Deterministic Policies With Stochastic Policy Gradients (2024)0.00
• Let's Play Again: Variability Of Deep Reinforcement Learning Agents In Atari Environments (2019)0.00
• Deterministic Policy Gradient For Reinforcement Learning With Continuous Time And State (2025)0.00
• Never Worse, Mostly Better: Stable Policy Improvement In Deep Reinforcement Learning (2019)0.00
• What Matters In On-policy Reinforcement Learning? A Large-scale Empirical Study (2020)0.00
• Identifying Policy Gradient Subspaces (2024)0.00