Inverse Reinforcement Learning with Locally Consistent Reward Functions

Authors: Quoc Phong Nguyen, Bryan Kian Hsiang Low, Patrick Jaillet

NeurIPS 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Empirical evaluation on synthetic and real-world datasets shows that our IRL algorithm outperforms the state-of-the-art EM clustering with maximum likelihood IRL, which is, interestingly, a reduced variant of our approach.
Researcher Affiliation Academia Dept. of Computer Science, National University of Singapore, Republic of Singapore Dept. of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, USA
Pseudocode No The paper describes the EM algorithm mathematically and textually but does not include a formal pseudocode block or algorithm listing.
Open Source Code No The paper does not provide any explicit statements or links indicating that source code for the described methodology is publicly available.
Open Datasets No The paper uses 'synthetic and real-world datasets', including 'GPS traces of 59 taxis' provided by 'The Comfort taxi company in Singapore', but does not provide concrete access information (link, DOI, or formal citation with authors/year) for public access to these datasets.
Dataset Splits No The paper evaluates performance on the 'expert’s demonstrated trajectories' and uses Ntot as the total number of trajectories but does not specify any explicit train/validation/test dataset splits for model evaluation.
Hardware Specification No The paper does not provide specific details about the hardware (e.g., GPU/CPU models, memory) used for running its experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers (e.g., programming languages, libraries, or solvers with their versions) that were used for the experiments.
Experiment Setup Yes We set γ to 0.95 and the number |R| of reward functions of the agent to 2. To avoid local maxima in gradient ascent, we initialize our EM algorithm with 20 random 0 values and report the best result based on the Q value of EM (Section 3).