Research map / Reinforcement learning / Visual and representation RL
Self-Predictive Universal AI
Elliot Catt, Jordi Grau-Moya, Marcus Hutter, Matthew Aitchison, Tim Genewein, Gregoire Deletang, Li Kevin Wenliang, Joel Veness
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 |
|---|---|---|---|
| add self-prediction (CTW policy prediction in rollouts) replacing uniform random rollouts | MC-AIXI · Cheese Maze | average reward per step: -1.0 -> 1.08 | Improved |
| add self-prediction in rollouts | MC-AIXI · Tiger | average reward per step: -0.29 -> 0.5 | Improved |
| add self-prediction in rollouts | MC-AIXI · 4x4 Grid | average reward per step: 0.0 -> 0.24 | Improved |
| add self-prediction in rollouts | MC-AIXI · Kuhn Poker | average reward per step: 1.98 -> 1.93 | No clear effect |
| add self-prediction in rollouts | MC-AIXI · Biased Scissor Paper Rock | average reward per step: 0.17 -> 0.22 | No clear effect |
Closest papers by meaning
- Oracle-Efficient Reinforcement Learning for Max Value Ensembles (NeurIPS 2024 · similarity 0.86)
- Data-Efficient Reinforcement Learning with Self-Predictive Representations (ICLR 2021 · similarity 0.86)
- SPO: Sequential Monte Carlo Policy Optimisation (NeurIPS 2024 · similarity 0.85)
- Autonomous Option Invention for Continual Hierarchical Reinforcement Learning and Planning (AAAI 2025 · similarity 0.84)
- Proto Successor Measure: Representing the Behavior Space of an RL Agent (ICML 2025 · similarity 0.83)
- OptionZero: Planning with Learned Options (ICLR 2025 · similarity 0.83)
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.
