Revisiting Design Choices In Proximal Policy Optimization

Abstract

Proximal Policy Optimization (PPO) is a popular deep policy gradient algorithm. In standard implementations, PPO regularizes policy updates with clipped probability ratios, and parameterizes policies with either continuous Gaussian distributions or discrete Softmax distributions. These design choices are widely accepted, and motivated by empirical performance comparisons on MuJoCo and Atari benchmarks. We revisit these practices outside the regime of current benchmarks, and expose three failure modes of standard PPO. We explain why standard design choices are problematic in these cases, and show that alternative choices of surrogate objectives and policy parameterizations can prevent the failure modes. We hope that our work serves as a reminder that many algorithmic design choices in reinforcement learning are tied to specific simulation environments. We should not implicitly accept these choices as a standard part of a more general algorithm.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyhsu2020revisiting

Related papers

• Proximal Policy Optimization Algorithms (2017)0.00
• Truly Proximal Policy Optimization (2019)0.00
• Policy Optimization With Model-based Explorations (2018)5.84
• ANO: A Principled Approach To Robust Policy Optimization (2026)0.00
• On Proximal Policy Optimization's Heavy-tailed Gradients (2021)0.00
• Proximal Policy Optimization Via Enhanced Exploration Efficiency (2020)13.70
• Implementation Matters In Deep Policy Gradients: A Case Study On PPO And TRPO (2020)0.00
• KIPPO: Koopman-inspired Proximal Policy Optimization (2025)0.00