Research map / Reinforcement learning / Policy gradient and actor-critic
Constrained Reinforcement Learning in Hard Exploration Problems
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 HiLiTE instead of Unsafe-HRL | Four Rooms · Four Rooms, cost limit 30 | expected cost | Helped |
| Use HiLiTE instead of BVF or Lyapunov | Four Rooms · Four Rooms, cost limit 30 | constraint satisfaction | Helped |
| Use HiLiTE instead of BVF or Lyapunov | Grid · Grid, 3 or 7 sub-goals; cost limits 60 or 90 | expected reward | Helped |
| Use HiLiTE instead of BVF or Lyapunov | Grid · Grid, 3 or 7 sub-goals; cost limits 60 or 90 | constraint satisfaction | Helped |
| Use HiLiTE instead of BVF | Puddle · Puddle, cost limit 20 | goal-reaching reward | Helped |
| Use HiLiTE instead of Lyapunov | Puddle · Puddle, cost limit 20 | constraint satisfaction | Helped |
| Use HiLiTE with 3 rather than 7 sub-goals (ablation) | HiLiTE · Grid, cost limits 60 and 90 | expected reward | No clear effect |
Closest papers by meaning
- Reward Penalties on Augmented States for Solving Richly Constrained RL Effectively (AAAI 2024 · similarity 0.92)
- Handling Long and Richly Constrained Tasks through Constrained Hierarchical Reinforcement Learning (AAAI 2024 · similarity 0.91)
- Constrained Reinforcement Learning Under Model Mismatch (ICML 2024 · similarity 0.90)
- Safe Reinforcement Learning with Instantaneous Constraints: The Role of Aggressive Exploration (AAAI 2024 · similarity 0.90)
- Controlling Underestimation Bias in Constrained Reinforcement Learning for Safe Exploration (ICML 2025 · similarity 0.89)
- Last-Iterate Global Convergence of Policy Gradients for Constrained Reinforcement Learning (NeurIPS 2024 · 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.