Hierarchical Reinforcement Learning With Multi Discount Factors In A Differential Game
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Reinforcement learning (RL) is an approach to solving differential games, especially pursuit-evasion games. Re-inforcement learning, treats the model and the environment as black boxes. It is shown that using multi-agent reinforcement learning is a suitable tool to address pursuit-evasion games. This paper proposes a new approach based on hierarchical reinforcement learning to find an instantaneous reward function for the game of guarding a territory, which is a more complex version of pursuit-evasion games. To have greater control over the generated path, a novel modification to the fuzzy actor-critic learning algorithm is proposed, so the augmented algorithm is able to handle several reward functions with different time horizons. The proposed approach has shown to have a suitable control over the combination of a terminal reward function and an instantaneous reward.
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.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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 it