Research map / Reinforcement learning / Policy gradient and actor-critic
Parameterized Indexed Value Function for Efficient Exploration in Reinforcement Learning
Tian Tan, Zhihan Xiong, Vikranth R. Dwaracherla
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 PINs instead of ensemble sampling | Deep-sea · Deep-sea | cumulative reward | No clear effect |
| Use PINs instead of ensemble sampling | Cartpole Swing-up · Cartpole Swing-up | episodic reward | No clear effect |
| Use a sampled-value action for target selection instead of the mean-value action (ablation) | PINs · Deep-sea | performance robustness across seeds | Hurt |
| Add a prior mechanism to bootstrapped DQN | Bootstrapped DQN on Deep-sea · Deep-sea | optimal-policy learning as problem size increases | Improved |
| Use PINs rather than BSP_K | Cartpole Swing-up · Cartpole Swing-up | variance in performance by end of learning | Improved |
Closest papers by meaning
- Deep Exploration via Randomized Value Functions (JMLR 2019 · similarity 0.90)
- Generalization and Exploration via Randomized Value Functions (ICML 2016 · similarity 0.89)
- Exploring through Random Curiosity with General Value Functions (NeurIPS 2022 · similarity 0.88)
- Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo (ICLR 2024 · similarity 0.87)
- Random Latent Exploration for Deep Reinforcement Learning (ICML 2024 · similarity 0.87)
- Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RL (NeurIPS 2025 · similarity 0.87)
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.
