Teaching to Learn: Sequential Teaching of Learners with Internal States
Authors: Mustafa Mert Çelikok, Pierre-Alexandre Murena, Samuel Kaski
AAAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Our empirical results demonstrate that our framework is able to reduce the number of required tasks for online meta-learning, and increases independent learning performance of simulated human users in future tasks. |
| Researcher Affiliation | Academia | Mustafa Mert C elikok1, Pierre-Alexandre Murena1, Samuel Kaski1, 2 1 Aalto University 2 The University of Manchester |
| Pseudocode | No | The paper describes algorithms in text (e.g., 'Algorithm. In the POMDP...', 'Algorithm. The interaction again defines a sequential leader-follower game.'), but does not provide structured pseudocode or an explicit algorithm block. |
| Open Source Code | No | The paper does not provide a specific link to open-source code for the described methodology or state that it is publicly available. |
| Open Datasets | No | The paper describes data generation methods from cited works (e.g., 'Ghosh and Ghattas (2015)', 'Finn, Abbeel, and Levine (2017)') but does not provide concrete access information (link, DOI, repository, or specific dataset citation) for a publicly available or open dataset used in its experiments. |
| Dataset Splits | No | The paper does not provide specific dataset split information (exact percentages, sample counts, citations to predefined splits, or detailed splitting methodology) for training, validation, or testing. |
| Hardware Specification | No | The paper mentions 'computational resources provided by the Aalto Science-IT Project' but does not provide specific details on hardware components like GPU or CPU models used for experiments. |
| Software Dependencies | No | The paper does not provide specific ancillary software details with version numbers (e.g., library or solver names with versions). |
| Experiment Setup | Yes | All results have been replicated with 10 random seeds and we present averaged values with 95% confidence intervals (CI). [...] Unless stated otherwise, the value for η is 0.5. [...] We set u1 = 0.5, u2 = 0.5, hence, the current and future performances are considered equally important. [...] We have limited the number of tasks to 50... |