Reinforcement Learning on Multiple Correlated Signals
Authors: Tim Brys, Ann Nowé
AAAI 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | The technique was shown to improve performance on a traffic light control problem, a natural CMOMDP, as well as on the Pursuit domain, an example of a single-objective MDP framed as a multi-objective problem using multiple shaping functions. Furthermore, the technique s objective selection decisions yield intuitive insights into the nature of the problems being solved, e.g. indicating where in the state space each shaping function correlates best with the value function. ... Initial results with adaptive objective selection in the first two domains are promising. ... Initial experiments in Mountain Car and the Pursuit domain also show promising results for ensemble techniques. |
| Researcher Affiliation | Academia | Tim Brys and Ann Now e Vrije Universiteit Brussel {timbrys, anowe}@vub.ac.be |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any concrete access to source code (e.g., specific repository link, explicit code release statement, or code in supplementary materials) for the methodology described. |
| Open Datasets | No | The paper mentions problem domains like 'traffic light control problem', 'Pursuit domain', 'Mountain Car', 'Keep Away', and 'Star Craft'. However, it does not provide concrete access information (specific link, DOI, repository name, formal citation with authors/year) for publicly available or open datasets used in these domains. |
| Dataset Splits | No | The paper does not provide specific dataset split information (exact percentages, sample counts, citations to predefined splits, or detailed splitting methodology) needed to reproduce the data partitioning. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments. |
| Software Dependencies | No | The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers like Python 3.8, CPLEX 12.4) needed to replicate the experiment. |
| Experiment Setup | No | The paper does not contain specific experimental setup details, such as concrete hyperparameter values, training configurations, or system-level settings. |