Research map / Reinforcement learning / MDPs and planning
Explicit Explore-Exploit Algorithms in Continuous State Spaces
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 |
|---|---|---|---|
| explore with model disagreement instead of uniform exploration (ablation) | Neural-E3 model-based agent · Maze (RGB images, random mazes) | reward | Helped |
| Neural-E3 vs DQN/PPO/PPO+RND on antishaped-reward combination lock | Neural-E3 · Stochastic combination lock, antishaped rewards, long horizons | reward | Helped |
| Neural-E3 vs DQN on Acrobot | Neural-E3 · Acrobot | sample efficiency | No clear effect |
| Neural-E3 vs DQN on MountainCar | Neural-E3 · MountainCar | episodes to solve: around 1200 -> under 300 episodes | Helped |
Closest papers by meaning
- FLEX: an Adaptive Exploration Algorithm for Nonlinear Systems (ICML 2023 · similarity 0.91)
- Model-Free Active Exploration in Reinforcement Learning (NeurIPS 2023 · similarity 0.91)
- Reward-Free Exploration for Reinforcement Learning (ICML 2020 · similarity 0.90)
- Temporally-Extended ε-Greedy Exploration (ICLR 2021 · similarity 0.90)
- Exploration via Planning for Information about the Optimal Trajectory (NeurIPS 2022 · similarity 0.90)
- LLM-Explorer: A Plug-in Reinforcement Learning Policy Exploration Enhancement Driven by Large Language Models (NeurIPS 2025 · 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.