Research map / Reinforcement learning / Visual and representation RL
Generative Exploration and Exploitation
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 |
|---|---|---|---|
| Add GENE's generated novel and unskilled start states | PPO · Maze | episodes to solve | Helped |
| Add GENE's generated start states | TRPO · Maze Ant | task performance | Helped |
| Add GENE's generated start states | MADDPG · Cooperative Navigation | episodes to solve | Helped |
| Use only novel-state generation and omit unskilled-state replay (ablation) | GENE on PPO · Maze | episodes to solve | Hurt |
| Generate the ant's joint positions and velocities in addition to 2D positions (ablation) | GENE on TRPO · Maze Ant | early-stage learning speed | Helped |
| Set the generated-start probability p to 0 instead of using generated starts (ablation) | PPO · Maze | ability to solve | Hurt |
| Use a small generated-start probability p (ablation) | GENE on PPO · Maze | effect of changing start-state distribution | No clear effect |
| Set the generated-start probability p too high (ablation) | GENE on PPO · Maze | episodes to solve | Hurt |
Closest papers by meaning
- DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning (NeurIPS 2025 · similarity 0.91)
- Decoupling Exploration and Policy Optimization: Uncertainty Guided Tree Search for Hard Exploration (NeurIPS 2026 · similarity 0.90)
- First-Explore, then Exploit: Meta-Learning to Solve Hard Exploration-Exploitation Trade-Offs (NeurIPS 2024 · similarity 0.89)
- Off-policy Reinforcement Learning with Model-based Exploration Augmentation (NeurIPS 2025 · similarity 0.88)
- Beyond Optimism: Exploration With Partially Observable Rewards (NeurIPS 2024 · similarity 0.87)
- A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoals (ICLR 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.