Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Online Action Recognition
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Make predicates partially observable by hiding 0 to 5 predicate interpretations | OARU · sokoban | precision (%): 90 ± 3 -> 89 ± 12 | Hurt |
| Make predicates partially observable by hiding 0 to 5 predicate interpretations | OARU · sokoban | recall (%): 91 ± 2 -> 86 ± 5 | Hurt |
| Make predicates partially observable by hiding 0 to 5 predicate interpretations | OARU · minecraft | precision (%): 97 ± 6 -> 65 ± 23 | Hurt |
| Make predicates partially observable by hiding 0 to 5 predicate interpretations | OARU · minecraft | recall (%): 100 ± 0 -> 99 ± 6 | No clear effect |
| Make predicates partially observable by hiding 0 to 5 predicate interpretations | OARU · travel | precision (%): 84 ± 15 -> 68 ± 27 | Hurt |
| Make predicates partially observable by hiding 0 to 5 predicate interpretations | OARU · travel | recall (%): 89 ± 11 -> 85 ± 10 | Hurt |
| Merge similar Up and Down actions into one generalized action | OARU · elevator | recall (%) | Hurt |
| Use partial observability rather than full observability | OARU · all nine domains | recognition time | Hurt |
| Generalize initial Trivial Grounded Actions through repeated unification | OARU · partial-observability convergence evaluation | CPU time | Helped |
Closest papers by meaning
- Learning Planning Domains from Non-redundant Fully-Observed Traces: Theoretical Foundations and Complexity Analysis (AAAI 2024 · similarity 0.87)
- Learning Planning Abstractions from Language (ICLR 2024 · similarity 0.87)
- Differentiable Learning of Lifted Action Schemas for Classical Planning (NeurIPS 2026 · similarity 0.86)
- Embodied Task Planning via Graph-Informed Action Generation with Large Language Models (ICML 2026 · similarity 0.85)
- Agent Planning with World Knowledge Model (NeurIPS 2024 · similarity 0.85)
- Interpreting Emergent Planning in Model-Free Reinforcement Learning (ICLR 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.