Research map / Reinforcement learning / MDPs and planning
PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning
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 |
|---|---|---|---|
| Use PC-PG instead of PPO | Policy gradient on the Bidirectional Diabolical Combination Lock · Bidirectional Diabolical Combination Lock, H=2 | success rate: 1.0 -> 1.0 | No clear effect |
| Use PC-PG instead of PPO | Policy gradient on the Bidirectional Diabolical Combination Lock · Bidirectional Diabolical Combination Lock, H=5 | success rate: 0.0 -> 1.0 | Helped |
| Use PC-PG instead of PPO | Policy gradient on the Bidirectional Diabolical Combination Lock · Bidirectional Diabolical Combination Lock, H=10 | success rate: 0.0 -> 1.0 | Helped |
| Use PC-PG instead of PPO | Policy gradient on the Bidirectional Diabolical Combination Lock · Bidirectional Diabolical Combination Lock, H=15 | success rate: 0.0 -> 1.0 | Helped |
| Use PC-PG instead of PPO+RND | Policy gradient on the Bidirectional Diabolical Combination Lock · Bidirectional Diabolical Combination Lock, H=2 | success rate: 0.75 -> 1.0 | Helped |
| Use PC-PG instead of PPO+RND | Policy gradient on the Bidirectional Diabolical Combination Lock · Bidirectional Diabolical Combination Lock, H=5 | success rate: 0.40 -> 1.0 | Helped |
| Use PC-PG instead of PPO+RND | Policy gradient on the Bidirectional Diabolical Combination Lock · Bidirectional Diabolical Combination Lock, H=10 | success rate: 0.50 -> 1.0 | Helped |
| Use PC-PG instead of PPO+RND | Policy gradient on the Bidirectional Diabolical Combination Lock · Bidirectional Diabolical Combination Lock, H=15 | success rate: 0.55 -> 1.0 | Helped |
Closest papers by meaning
- Learning Optimal Deterministic Policies with Stochastic Policy Gradients (ICML 2024 · similarity 0.91)
- Last-Iterate Global Convergence of Policy Gradients for Constrained Reinforcement Learning (NeurIPS 2024 · similarity 0.90)
- Convergence Analysis of Policy Gradient Methods with Dynamic Stochasticity (ICML 2025 · similarity 0.90)
- Scalable Online Exploration via Coverability (ICML 2024 · similarity 0.90)
- Occupancy-based Policy Gradient: Estimation, Convergence, and Optimality (NeurIPS 2024 · similarity 0.89)
- Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient Data Utilization (ICML 2024 · 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.