Comparative Study of Reinforcement Learning Performance Based on PPO and DQN Algorithms
Bibliographic record
Abstract
With the rapid development of artificial intelligence technology, reinforcement learning (RL) has emerged as a core research direction in the field of intelligent decision-making. Among numerous reinforcement learning algorithms, Deep Q-Network (DQN) and Proximal Policy Optimization (PPO) have gained widespread attention due to their outstanding performance. These two algorithms have been extensively applied in areas such as autonomous driving and game AI, demonstrating strong adaptability and effectiveness. However, despite numerous application instances, systematic comparative studies on their specific performance differences remain relatively scarce. This study aims to systematically evaluate the differences between DQN and PPO algorithms across four performance metrics: convergence speed, stability, sample efficiency, and computational complexity. By combining theoretical analysis and experimental validation, we selected classic reinforcement learning environments—CartPole (for discrete action testing) and CarRacing (for continuous action evaluation)—to conduct a detailed performance assessment. The results show that DQN exhibits superior performance in discrete action environments with faster convergence and higher sample efficiency, whereas PPO demonstrates greater stability and adaptability in continuous action environments.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.017 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".