Research map / Reinforcement learning / Policy gradient and actor-critic
Deep Bayesian Quadrature Policy Optimization
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 Monte Carlo gradient estimation with DBQPG | Vanilla PG, NPG, and TRPO · MuJoCo (7 domains) | average return | Helped |
| Replace Monte Carlo gradient estimation with DBQPG | Vanilla PG, NPG, and TRPO · MuJoCo (7 domains) | sample complexity | Helped |
| Use DBQPG instead of Monte Carlo for gradient estimation | Policy gradient estimation · MuJoCo Swimmer-v2 | gradient accuracy | Helped |
| Use DBQPG instead of Monte Carlo for gradient estimation | Policy gradient estimation · MuJoCo Swimmer-v2 | normalized gradient variance | Helped |
| Add uncertainty-based gradient normalization | DBQPG in vanilla PG and NPG · MuJoCo | average return | Helped |
| Add uncertainty-based gradient normalization | DBQPG in TRPO · MuJoCo | average return | No clear effect |
Closest papers by meaning
- Optimal Estimation of Policy Gradient via Double Fitted Iteration (ICML 2022 · similarity 0.89)
- Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic (ICLR 2017 · similarity 0.88)
- PAGE-PG: A Simple and Loopless Variance-Reduced Policy Gradient Method with Probabilistic Gradient Estimation (ICML 2022 · similarity 0.88)
- Adaptive-Gradient Policy Optimization: Enhancing Policy Learning in Non-Smooth Differentiable Simulations (ICML 2024 · similarity 0.87)
- Momentum-Based Policy Gradient Methods (ICML 2020 · similarity 0.87)
- Deep Policy Gradient Methods Without Batch Updates, Target Networks, or Replay Buffers (NeurIPS 2024 · 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.