Check the preview of 2nd version of this platform
being developed by the open MLCommons taskforce on automation and reproducibility
as a free, open-source and technology-agnostic on-prem platform.
A Demonstration of Issues with Value-Based Multiobjective Reinforcement Learning Under Stochastic State Transitions
lib:b8dbc9e29ccb60bc (v1.0.0)
Authors: Peter Vamplew,Cameron Foale,Richard Dazeley
ArXiv: 2004.06277
Document: PDF DOI
Abstract URL: https://arxiv.org/abs/2004.06277v1
We report a previously unidentified issue with model-free, value-based approaches to multiobjective reinforcement learning in the context of environments with stochastic state transitions. An example multiobjective Markov Decision Process (MOMDP) is used to demonstrate that under such conditions these approaches may be unable to discover the policy which maximises the Scalarised Expected Return, and in fact may converge to a Pareto-dominated solution. We discuss several alternative methods which may be more suitable for maximising SER in MOMDPs with stochastic transitions.
ArXiv: 2004.06277
Document: PDF DOI
Abstract URL: https://arxiv.org/abs/2004.06277v1
We report a previously unidentified issue with model-free, value-based approaches to multiobjective reinforcement learning in the context of environments with stochastic state transitions. An example multiobjective Markov Decision Process (MOMDP) is used to demonstrate that under such conditions these approaches may be unable to discover the policy which maximises the Scalarised Expected Return, and in fact may converge to a Pareto-dominated solution. We discuss several alternative methods which may be more suitable for maximising SER in MOMDPs with stochastic transitions.
Relevant initiatives
Related knowledge about this paper
Reproduced results (crowd-benchmarking and competitions)
Artifact and reproducibility checklists
- ACM/cTuning artifact appendix and reproducibility checklist
- NeurIPS reproducibility checklist
- SIGPLAN's checklist for empirical evaluation
- Collective Knowledge (organizing research projects based on FAIR principles)