Research map / Reinforcement learning / Policy gradient and actor-critic
Bayesian Distributional Policy Gradients
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 BDPG with posterior information-gain curiosity instead of naive exploration | BDPG · Atari hard-exploration games | score | Helped |
| Use Bayesian inference-based return estimation instead of WGAN or quantile regression | Atari games · 8 Atari games | score | Mixed |
| Use Bayesian inference-based return estimation instead of WGAN | BDPG naive · MuJoCo tasks | score | Helped |
| Use a longer bootstrap length instead of a short bootstrap length (ablation) | BDPG · Breakout and Q*bert | average score | Helped |
| Set bootstrap length to 1 (ablation) | BDPG · Breakout and Q*bert | average score | Hurt |
| Use an excessively large bootstrap length (ablation) | BDPG · Breakout and Q*bert | average score | No clear effect |
| Remove the information-gain truncation cap (ablation) | BDPG · Breakout and Q*bert | average score | Hurt |
| Combine a long bootstrap length with a large information-gain cap (ablation) | BDPG · Breakout and Q*bert | average score | Hurt |
Closest papers by meaning
- Distributional Reinforcement Learning With Quantile Regression (AAAI 2018 · similarity 0.92)
- Intrinsic Benefits of Categorical Distributional Loss: Uncertainty-aware Regularized Exploration in Reinforcement Learning (NeurIPS 2025 · similarity 0.90)
- Diverse Projection Ensembles for Distributional Reinforcement Learning (ICLR 2024 · similarity 0.89)
- Near-Minimax-Optimal Distributional Reinforcement Learning with a Generative Model (NeurIPS 2024 · similarity 0.89)
- A Distributional Analogue to the Successor Representation (ICML 2024 · similarity 0.89)
- Distributional Reinforcement Learning with Regularized Wasserstein Loss (NeurIPS 2024 · similarity 0.88)
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.