Goal Recognition Design with Stochastic Agent Action Outcomes

Authors: Christabel Wayllace, Ping Hou, William Yeoh, Tran Cao Son

IJCAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We evaluated our REDUCE-WCD algorithm with and without the optimization on Line 30 (labeled R-W(o) and R-W( o), respectively) on the same four deterministic benchmarks domains [Keren et al., 2014], except that we modified them to allow for stochastic actions, where each action can transition to its deterministic successor with probability 0.9 and stay in the same state with probability 0.1. [...] Table 1 tabulates the results.
Researcher Affiliation Academia New Mexico State University Las Cruces, NM 88003, USA {cwayllac, phou, wyeoh, tson}@cs.nmsu.edu
Pseudocode Yes Algorithm 1: FIND-WCD(P = h D, Gi) [...] Algorithm 2: REDUCE-WCD(P = h D, Gi, k)
Open Source Code No The paper does not provide concrete access to source code for the methodology described.
Open Datasets Yes We evaluated our REDUCE-WCD algorithm with and without the optimization on Line 30 (labeled R-W(o) and R-W( o), respectively) on the same four deterministic benchmarks domains [Keren et al., 2014]
Dataset Splits No The paper evaluates on 'deterministic benchmarks domains' and their 'instances' but does not specify any training, validation, or test dataset splits. The problem is framed as an offline design problem, not a machine learning task with data splitting.
Hardware Specification Yes The experiments were conducted on a 3.1GHz quad-core machine with 6GB of RAM and a timeout of 2 days was set.
Software Dependencies No The paper mentions general techniques like MDPs and ASP, but does not provide specific software names with version numbers (e.g., 'PyTorch 1.9', 'CPLEX 12.4') that were used for implementation or experimentation.
Experiment Setup Yes We evaluated our REDUCE-WCD algorithm... except that we modified them to allow for stochastic actions, where each action can transition to its deterministic successor with probability 0.9 and stay in the same state with probability 0.1. [...] The experiments were conducted on a 3.1GHz quad-core machine with 6GB of RAM and a timeout of 2 days was set. [...] First, it limits the maximum number of actions to make infeasible to a user-defined parameter k.