Research map / Reinforcement learning / MDPs and planning
Steady State Analysis of Episodic Reinforcement Learning
Huang Bojun
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 |
|---|---|---|---|
| Omit the average-episode-length (AEL) term from the SSPG gradient estimator (ablation) | SSPG estimator · RoboSchoolBullet Hopper | gradient bias vs ground truth: 7 | Hurt |
| Apply recursive perturbation with epsilon=1-1/E[T] | RoboSchoolBullet Humanoid · RoboSchoolBullet Humanoid | steady-state convergence time: 24 -> 3 | Improved |
| Apply recursive perturbation with epsilon=1-1/E[T] | RoboSchoolBullet HalfCheetah · RoboSchoolBullet HalfCheetah | steady-state convergence | Improved |
| Apply recursive perturbation with epsilon=1-1/n | Synthetic round-robin environment · Synthetic environment, n=20 to 2000 | uniformity of state distribution at t=3n | Improved |
| Apply perturbation to Hopper | RoboSchoolBullet Hopper · RoboSchoolBullet Hopper | steady-state convergence time | No clear effect |
Closest papers by meaning
- Ergodic Risk Measures: Towards a Risk-Aware Foundation for Continual Reinforcement Learning (NeurIPS 2026 · similarity 0.83)
- Open the Black Box: Step-based Policy Updates for Temporally-Correlated Episodic Reinforcement Learning (ICLR 2024 · similarity 0.81)
- On-Policy Algorithms for Continual Reinforcement Learning (Student Abstract) (AAAI 2025 · similarity 0.81)
- DynaMITE-RL: A Dynamic Model for Improved Temporal Meta-Reinforcement Learning (NeurIPS 2024 · similarity 0.81)
- When Does Non-Uniform Replay Matter in Reinforcement Learning? (NeurIPS 2026 · similarity 0.81)
- Position: Lifetime tuning is incompatible with continual reinforcement learning (ICML 2025 · similarity 0.81)
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.
