Research map / Reinforcement learning / Policy gradient and actor-critic
Predictor-Corrector Policy Optimization
Ching-An Cheng, Xinyan Yan, Nathan Ratliff, Byron Boots
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 |
|---|---|---|---|
| Use PicCoLO prediction and error-correction steps instead of the model-free update | first-order policy optimization · Predictable online learning (theory) | average regret upper bound: \frac{1}{\sqrt{N}} \paren{\abs{\Pi} + G_g^2 + \sigma_g^2} -> \frac{1}{\sqrt{N}} \paren{\abs{\Pi} + \sigma_g^2 + \sigma_{ | Improved |
| Use an accurate predictive model | PicCoLO with Adam · CartPole | sum of rewards | Improved |
| Use an adversarial predictive model (ablation) | PicCoLO with Adam · CartPole | sum of rewards | No clear effect |
| Use an adversarial predictive model (ablation) | Dyna with Adam · CartPole | sum of rewards | Hurt |
| Compute the predicted gradient with the fixed-point formulation rather than Φ(π̂_n) (ablation) | PicCoLO · CartPole | sum of rewards | Improved |
| Compute the predicted gradient with the fixed-point formulation rather than Φ(π̂_n) (ablation) | PicCoLO · Robot RL tasks | sum of rewards | Improved |
| PicCoLO a base optimizer using predictive gradients | Adam, Natgrad, and trpo · Hopper, Snake, and Walker3D | sum of rewards | Improved |
| Use predictive gradients from a biased dynamics model with fixed-point prediction (ablation) | PicCoLO · Robot RL tasks | sum of rewards | Mixed |
Closest papers by meaning
- Neural Predictor-Corrector: Solving Homotopy Problems with Reinforcement Learning (ICLR 2026 · similarity 0.89)
- Adversarial Imitation Learning With General Function Approximation: Theoretical Analysis and Practical Algorithms (TPAMI 2026 · similarity 0.87)
- Hybrid Inverse Reinforcement Learning (ICML 2024 · similarity 0.86)
- Dual RL: Unification and New Methods for Reinforcement and Imitation Learning (ICLR 2024 · similarity 0.86)
- Pre-Trained Multi-Goal Transformers with Prompt Optimization for Efficient Online Adaptation (NeurIPS 2024 · similarity 0.86)
- Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model (ICLR 2025 · similarity 0.86)
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.
