Leveraging Observational Learning for Exploration in Bandits
Bibliographic record
Abstract
Learning from a target has been tackled in the reinforcement learning (RL) setting [1, 7] as imitation learning, either through behaviour cloning or inverse RL. In the former, the agent regresses directly onto the policy of a target [5], while in the latter, the agent infers a reward function from the behaviour of other agents and optimizes this function [6]. Extending upon these notions, observational learning was recently introduced in RL as the ability for an agent to modify its behavior or to acquire information as an effect of observing another agent sharing its environment [3]. In this work, we study the observational learning problem under the bandit setting. More specifically, we consider a learner (agent) that has access to actions performed by a target policy in the same environment. The agent only observes the target's actions, but not their associated rewards. Note that the target actions can in fact be performed by several other agents. This should not be confused with cooperative bandits [4], where several agents share knowledge with each other regarding the actions and obtained rewards.
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 | 0.000 | 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 | 0.001 |
| Open science | 0.000 | 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".