Research map / Reinforcement learning / Visual and representation RL
Heuristic-Guided 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 HuRL with an engineered distance heuristic and a scheduled shorter horizon | SAC · Sparse-Reacher-v2 | undiscounted cumulative return | Helped |
| Use HuRL with a Monte-Carlo value heuristic | SAC with BC warm start · Hopper-v2, HalfCheetah-v2, Humanoid-v2, and Swimmer-v2 | undiscounted cumulative return | Mixed |
| Warm-start SAC with behavior cloning | SAC · Dense-reward MuJoCo environments | undiscounted cumulative return | Helped |
| Use behavior cloning alone instead of online RL | BC · Dense-reward MuJoCo environments | undiscounted cumulative return | Hurt |
| Add a scheduled shorter horizon with a zero heuristic (ablation) | SAC with BC warm start · Dense-reward MuJoCo environments | undiscounted cumulative return | No clear effect |
| Apply PBRS reward shaping | SAC · MuJoCo experiments | undiscounted cumulative return | Hurt |
| Increase constant λ above 0.98 (ablation) | HuRL-MC · Hopper-v2 | undiscounted cumulative return | Hurt |
Closest papers by meaning
- Going Beyond Heuristics by Imposing Policy Improvement as a Constraint (NeurIPS 2024 · similarity 0.90)
- Dual RL: Unification and New Methods for Reinforcement and Imitation Learning (ICLR 2024 · similarity 0.89)
- Overcoming Slow Decision Frequencies in Continuous Control: Model-Based Sequence Reinforcement Learning for Model-Free Control (ICLR 2025 · similarity 0.88)
- Discovering Temporally-Aware Reinforcement Learning Algorithms (ICLR 2024 · similarity 0.88)
- Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes (AAAI 2025 · similarity 0.88)
- Oracle-Efficient Reinforcement Learning for Max Value Ensembles (NeurIPS 2024 · similarity 0.88)
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.