Real-Time Swing-up of a Linear Inverted Pendulum Using Reinforcement Learning
Bibliographic record
Abstract
This study focused on applying and enhancing the Deep Deterministic Policy Gradient (DDPG) algorithm to effectively control a Single Inverted Pendulum (SIP) system. The primary objective was to improve the algorithm's performance by addressing common challenges such as overestimation of Q-values and convergence to local optima. The system's behaviour was analyzed through simulation and real-world experiments, showcasing the algorithm's ability to offer faster responses, enhanced stability, and reduced pendulum displacement. The research introduced key modifications to the experience replay mechanism and the Critic network, which played a significant role in improving the efficiency of the learning process and the robustness of the control strategy. By combining Reinforcement Learning with traditional control methods, this approach successfully managed the nonlinear dynamics of the SIP system. Nevertheless, certain challenges persist, particularly in terms of the efficiency of deep reinforcement learning algorithms and their stability in real-world environments. These findings suggest that future research should focus on further refining DRL algorithms to increase their practical application in physical control systems. In conclusion, the research highlights the potential of combining DRL techniques with conventional control strategies for tackling complex control problems. The success achieved in controlling the SIP system indicates a promising direction for further exploration and development in this field.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 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".