Learning the Discount Factor in Inverse Reinforcement Learning with Application to Animal Behaviour
Bibliographic record
Abstract
Inverse reinforcement learning (IRL) focuses on recovering the agent's objective function through observed demonstrations, enabling us to better understand human and non-human animals' decision-making processes. However, an important aspect of decision-making---how we discount the future reward---has not been well-studied in IRL. In this thesis, we study the problem of IRL with unknown discount factor and develop its first application in animal behaviour. We investigate an existing work on IRL with unknown discount factor in detail, correcting several minor errors in the formulation and examining different mathematical characteristics of the problem. We propose an alternative algorithm for the correct gradient calculation, examine the convexity of the objective function in the optimization problem, and discuss the connections among different formulations of the objective functions seen in the literature. We then apply the framework to studying wild vervet monkeys' foraging behaviour in two different scenarios: foraging alone or in competition. We formulate and solve each scenario as an IRL problem. Our experimental results provide novel insights into vervet monkeys' cognitive decision-making process. We present several suggestions on future foraging experiment design to improve the current mathematical models.
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) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.003 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.000 | 0.003 |
| Insufficient payload (model declined to judge) | 0.000 | 0.001 |
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".