Research map / Reinforcement learning / Policy gradient and actor-critic
Variational Policy Gradient Method for Reinforcement Learning with General Utilities
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 |
|---|---|---|---|
| increase log-barrier penalty beta (0 -> 4) in constrained MDP (ablation) | Variational policy gradient with log barrier · Frozen Lake with costly states | test cost | Helped |
| increase log-barrier penalty beta (0 -> 4) in constrained MDP (ablation) | Variational policy gradient with log barrier · Frozen Lake with costly states | test reward | Hurt |
| maximize occupancy entropy with variational PG instead of uniform random policy | Frozen Lake exploration · Frozen Lake max entropy exploration | state coverage / entropy | Helped |
| more episodes for variational gradient estimator | Algorithm for policy gradient estimation · Frozen Lake | cosine similarity to true gradient | Helped |
Closest papers by meaning
- On the Global Optimality of Policy Gradient Methods in General Utility Reinforcement Learning (NeurIPS 2025 · similarity 0.92)
- Last-Iterate Global Convergence of Policy Gradients for Constrained Reinforcement Learning (NeurIPS 2024 · similarity 0.90)
- Occupancy-based Policy Gradient: Estimation, Convergence, and Optimality (NeurIPS 2024 · similarity 0.90)
- Generalizable Policy Improvement via Reinforcement Sampling (Student Abstract) (AAAI 2024 · similarity 0.89)
- On the Second-Order Convergence of Biased Policy Gradient Algorithms (ICML 2024 · similarity 0.89)
- Learning Optimal Deterministic Policies with Stochastic Policy Gradients (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.