Research map / Reinforcement learning / Policy gradient and actor-critic
Natural Actor-Critic for Robust Reinforcement Learning with Function Approximation
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 PPO with RNAC-PPO (DS uncertainty set) | PPO · TurtleBot, unbalanced noise | target reaching rate: 0\% -> 100\% | Helped |
| replace PPO with RNAC-PPO (IPM uncertainty set) | PPO · TurtleBot, unbalanced noise | target reaching rate: 0\% -> 100\% | Helped |
| use RNAC-PPO (DS) instead of action noise envelope | TurtleBot policy · TurtleBot, unbalanced noise | target reaching rate: 67.5\% -> 100\% | Helped |
| use RNAC-PPO (IPM) instead of dynamics randomization | TurtleBot policy · TurtleBot, unbalanced noise | target reaching rate: 2\% -> 100\% | Helped |
| add DS robust critic/actor (m=2, delta=1/6) to PPO | PPO · Stochastic MuJoCo Hopper/Walker2d/HalfCheetah under perturbation | cumulative reward | Mixed |
| add IPM regularized robust Bellman operator (delta=1e-5) to PPO | PPO · Deterministic MuJoCo environments under perturbation | cumulative reward | Helped |
| compare RNAC-PPO with SAC under gravity perturbation | RNAC-PPO · MuJoCo, gravity perturbation | cumulative reward decay | No clear effect |
| compare RNAC-PPO with SAC under leg_joint_stiffness perturbation | RNAC-PPO · MuJoCo, leg_joint_stiffness perturbation | cumulative reward decay | Helped |
| soft-robust PPO (distribution over uncertainty set) versus nominal-trained PPO | PPO · MuJoCo, nominal and leg_joint_stiffness perturbed | cumulative reward | Mixed |
Closest papers by meaning
- Time-Constrained Robust MDPs (NeurIPS 2024 · similarity 0.90)
- Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning (ICLR 2025 · similarity 0.89)
- Minimax Optimal and Computationally Efficient Algorithms for Distributionally Robust Offline Reinforcement Learning (NeurIPS 2024 · similarity 0.88)
- Sampling-Based Safe Reinforcement Learning (NeurIPS 2026 · similarity 0.88)
- Constrained Reinforcement Learning Under Model Mismatch (ICML 2024 · similarity 0.87)
- Robust Offline Reinforcement Learning with Linearly Structured $f$-Divergence Regularization (ICML 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.