Research map / Reinforcement learning / Visual and representation RL
EX2: Exploration with Exemplar Models for Deep Reinforcement Learning
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 EX² exploration bonuses instead of naive TRPO exploration | TRPO · SparseHalfCheetah | mean score: 0 -> 173.2 | Helped |
| Use EX² exploration bonuses instead of naive TRPO exploration | TRPO · SwimmerGather | mean score: 0 -> 0.240 | Helped |
| Use EX² amortized exploration instead of Hashing | Atari exploration · Freeway (Atari) | mean score: 33.5 vs 33.3 | No clear effect |
| Use EX² amortized exploration instead of Hashing | Atari exploration · Frostbite (Atari) | mean score: 5214 vs 4901 | No clear effect |
| Use EX² amortized exploration instead of Hashing | Atari exploration · Venture (Atari) | mean score: 445 vs 900 | Helped |
| Use EX² exploration bonuses instead of explicit generative novelty methods | DoomMyWayHome exploration · DoomMyWayHome | mean score: 0.443 -> 0.788 | Helped |
| Use EX² exploration instead of Gaussian exploration | TRPO · 2D Maze | mean score: -175.6 -> -104.2 | Helped |
Closest papers by meaning
- Exploratory Diffusion Model for Unsupervised Reinforcement Learning (ICLR 2026 · similarity 0.88)
- Task-Aware Exploration via a Predictive Bisimulation Metric (ICML 2026 · similarity 0.87)
- Novelty Detection in Reinforcement Learning with World Models (ICML 2025 · similarity 0.87)
- MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization (ICLR 2025 · similarity 0.87)
- DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning (NeurIPS 2025 · similarity 0.86)
- Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction (ICLR 2025 · 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.