Research map / Reinforcement learning / MDPs and planning
Robust Reinforcement Learning using Least Squares Policy Iteration with Provable Performance Guarantees
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 |
|---|---|---|---|
| Replace non-robust algorithms with RLSPI | CartPole, MountainCar, and Acrobot · Perturbed OpenAI Gym environments | performance under model perturbations | Helped |
| Use RLSPI instead of Q-learning or soft-robust DQN | CartPole · Random-action perturbations | average episodic reward | Mixed |
| Use RLSPI instead of DDPG or soft-robust DDPG | MountainCar · Random-action perturbations | average number of time steps to reach the goal | Mixed |
| Use RLSPI instead of DQN or soft-robust DQN | Acrobot · Random-action perturbations | average episodic reward | Mixed |
| Train RLSPI for nominal parameters and test with perturbed parameters | RLSPI · CartPole force_mag, gravity, and length perturbations | test performance | Helped |
Closest papers by meaning
- Robust Offline Reinforcement Learning with Linearly Structured $f$-Divergence Regularization (ICML 2025 · similarity 0.91)
- A Single-Loop Robust Policy Gradient Method for Robust Markov Decision Processes (ICML 2024 · similarity 0.90)
- Time-Constrained Robust MDPs (NeurIPS 2024 · similarity 0.90)
- Near-Optimal Distributionally Robust Reinforcement Learning with General $L_p$ Norms (NeurIPS 2024 · similarity 0.89)
- Model-Free Robust $\phi$-Divergence Reinforcement Learning Using Both Offline and Online Data (ICML 2024 · similarity 0.89)
- Provable Policy Gradient for Robust Average-Reward MDPs Beyond Rectangularity (ICML 2025 · similarity 0.89)
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.