Research map / Learning theory and algorithms / Prediction and decision losses
Learning Mixtures of Markov Chains and MDPs
Chinmaya Kausik, Kevin Tan, Ambuj Tewari
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use the proposed subspace-estimation and clustering pipeline instead of randomly initialized soft EM | 8x8 gridworld mixture · 8x8 gridworld mixture | average accuracy: 73.2% -> 96.6% | Improved |
| replace estimated projectors with the identity matrix (ablation) | Proposed method · 8x8 gridworld mixture | clustering error | Hurt |
| replace estimated projectors with a random projector (ablation) | Proposed method · 8x8 gridworld mixture | clustering error | Hurt |
| use estimated subspaces for trajectory clustering (ablation) | Proposed method · 8x8 gridworld mixture | clustering error | Improved |
| increase trajectory length past the reported transition region (ablation) | Proposed method · 8x8 gridworld mixture | clustering error: T_n=60 to T_n=70 | Improved |
| initialize soft EM with the proposed clustering and classification labels instead of random initialization (ablation) | Soft EM · 8x8 gridworld mixture | label accuracy | Improved |
| initialize soft EM with models estimated from clustered trajectories instead of random initialization (ablation) | Soft EM · 8x8 gridworld mixture | label accuracy: T_n > 60 | Improved |
| initialize soft EM with clustering labels while introducing uncertainty in the responsibilities (ablation) | Soft EM · 8x8 gridworld mixture | convergence | Improved |
Closest papers by meaning
- Learning Mixtures of Linear Dynamical Systems (ICML 2022 · similarity 0.88)
- Learning Multiple Markov Chains via Adaptive Allocation (NeurIPS 2019 · similarity 0.88)
- Infinity Learning: Learning Markov Chains from Aggregate Steady-State Observations (AAAI 2020 · similarity 0.87)
- Linear Mixture Distributionally Robust Markov Decision Processes (NeurIPS 2025 · similarity 0.86)
- Learning a Fast Mixing Exogenous Block MDP using a Single Trajectory (ICLR 2025 · similarity 0.85)
- Sequence Modeling with Spectral Mean Flows (NeurIPS 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
