Explainable Artificial Intelligence (XAI) Approach for Reinforcement Learning Systems
Bibliographic record
Abstract
This study highlights the significance of incorporating uncertainty in Explainable Artificial Intelligence (XAI) systems. To achieve our purpose, we utilize Bayesian deep learning and uncertainty-aware planning, which allow us to create visual indicators to demonstrate how autonomous agents perceive their surroundings and take action. We use a reinforcement learning method called DQN with uncertainty and compare the results with four other baseline algorithms: DQN, DDQN with Prioritised Replay, Dueling DDQN and DDQN. Our findings show that the uncertainty estimate can generate a more efficient and stable decision-making model. To explain the behaviour of our agent, we suggest an interface that displays the current view of the environment, the agent's view, Q-values for each possible action, state value, a heatmap relative to the agent's input, and a visual representation of the uncertainty connected with each Q-value. Our approach can enhance the human understanding of the algorithm's decision-making process and confidence in its performance.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".