Research map / Probabilistic and scientific modeling / Dynamical systems
Sparsely Changing Latent States for Prediction and Planning in Partially Observable Domains
Christian Gumbsch, Martin V. Butz, Georg Martius
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 GateL0RD with latent-state L0 regularization (λ=0.001) instead of standard RNNs | Billiard Ball · Billiard Ball | autoregressive prediction error | Improved |
| Use GateL0RD (λ=0.001) instead of standard RNNs | Robot Remote Control · Robot Remote Control test set | prediction error | Improved |
| Use GateL0RD (λ=0.001) instead of standard RNNs | Robot Remote Control · Robot Remote Control generalization set | prediction error | Improved |
| Use GateL0RD instead of standard RNNs | Robot Remote Control MPC · Robot Remote Control | success rate | Improved |
| Use GateL0RD (λ=0.0001) instead of standard RNNs | Shepherd · Shepherd 100-step prediction | prediction error | Improved |
| Use GateL0RD instead of standard RNNs | Shepherd MPC · Shepherd | success rate | Improved |
| Replace the LSTM memory module with GateL0RD (λ=0.01) | PPO actor-critic · MiniGrid tasks | success rate | Improved |
| Replace the LSTM memory module with GateL0RD (λ=0.01) | PPO actor-critic · MiniGrid tasks | sample efficiency | Improved |
| Set λ=0.001 rather than use stronger regularization (ablation) | GateL0RD · Billiard Ball | prediction error | Improved |
| Increase regularization strength to λ=0.1 (ablation) | GateL0RD · Billiard Ball | prediction error | Hurt |
| Vary regularization strength within λ∈[0, 0.01] (ablation) | GateL0RD · Billiard Ball | prediction error | No clear effect |
| Remove latent-state regularization (λ=0) (ablation) | GateL0RD · Fetch Pick&Place with continuously changing dynamics | prediction performance | Improved |
Closest papers by meaning
- Gated Inference Network: Inference and Learning State-Space Models (NeurIPS 2024 · similarity 0.87)
- Simplifying Latent Dynamics with Softly State-Invariant World Models (NeurIPS 2024 · similarity 0.86)
- The Wasserstein Believer: Learning Belief Updates for Partially Observable Environments through Reliable Latent Space Models (ICLR 2024 · similarity 0.86)
- HaM-World: Soft-Hamiltonian World Models with Selective Memory for Planning (NeurIPS 2026 · similarity 0.86)
- On Double Descent in Reinforcement Learning with LSTD and Random Features (ICLR 2024 · similarity 0.86)
- Measuring and Controlling Solution Degeneracy across Task-Trained Recurrent Neural Networks (NeurIPS 2025 · similarity 0.86)
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.
