Policy Gradient With Value Function Approximation For Collective Multiagent Planning
Authors: Duc Thien Nguyen, Akshat Kumar, Hoong Chuin Lau
NeurIPS 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Comparisons on a synthetic benchmark and a real world taxi fleet optimization problem show that our new AC approach provides better quality solutions than previous best approaches. and We test our approach on a synthetic multirobot grid navigation domain from (Nguyen et al., 2017), and a real world supply-demand taxi matching problem in a large Asian city with up to 8000 taxis (or agents) showing the scalability of our approach to large multiagent systems. Empirically, our new factored actor-critic approach works better than previous best approaches providing much higher solution quality. |
| Researcher Affiliation | Academia | Duc Thien Nguyen Akshat Kumar Hoong Chuin Lau School of Information Systems Singapore Management University 80 Stamford Road, Singapore 178902 {dtnguyen.2014,akshatkumar,hclau}@smu.edu.sg |
| Pseudocode | Yes | Algorithm 1: Actor-Critic RL for CDec-POMDPs |
| Open Source Code | No | The paper does not provide any concrete access information (specific repository link, explicit code release statement, or code in supplementary materials) for the methodology described. |
| Open Datasets | No | The paper mentions using 'GPS traces of taxi movement in a large Asian city over 1 year' and 'observed demand information extracted from this dataset' for the taxi supply-demand matching problem, referencing (Varakantham et al., 2012; Nguyen et al., 2017). It also uses 'a synthetic multirobot grid navigation domain from (Nguyen et al., 2017)'. However, it does not provide concrete access information (specific link, DOI, repository name, or explicit statement of public availability with proper citation for the dataset used in their experiments) for these datasets. |
| Dataset Splits | No | The paper discusses experimental results and convergence, but does not explicitly provide specific dataset split information (exact percentages, sample counts, citations to predefined splits, or detailed splitting methodology) needed to reproduce the data partitioning into train, validation, and test sets. |
| Hardware Specification | No | The paper does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments. |
| Software Dependencies | No | The paper mentions using a 'neural network' and 'reinforcement learning' but 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 states, 'The neural network structure and other experimental settings are provided in the appendix.' However, these specific experimental setup details (concrete hyperparameter values, training configurations, or system-level settings) are not present in the main text of the paper. |