Research map / Reinforcement learning / Visual and representation RL
Robust Predictable Control
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 |
|---|---|---|---|
| compress sequences with a predicted prior and information-augmented reward (RPC) instead of per-observation VIB | RPC · Walker, 0.3 bits | return: 530 -> 3,562 | Helped |
| use predictive prior with feedforward policy instead of LSTM-based VIB+RNN | RPC · Walker, 0.3 bits | return: 1,978 -> 3,562 | Helped |
| compress policy to fewer bits (0.3 vs 3.0 bits) | RPC · Ant robust RL (mass/friction) | return under perturbation | Mixed |
Closest papers by meaning
- Reinforcement Learning with Simple Sequence Priors (NeurIPS 2023 · similarity 0.92)
- The Variational Bandwidth Bottleneck: Stochastic Evaluation on an Information Budget (ICLR 2020 · similarity 0.89)
- Online Robust Reinforcement Learning with General Function Approximation (ICML 2026 · similarity 0.88)
- Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck (NeurIPS 2019 · similarity 0.88)
- Reinforcement Learning with Adaptive Regularization for Safe Control of Critical Systems (NeurIPS 2024 · similarity 0.88)
- Overcoming Slow Decision Frequencies in Continuous Control: Model-Based Sequence Reinforcement Learning for Model-Free Control (ICLR 2025 · similarity 0.87)
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.