Research map / Reinforcement learning / Visual and representation RL
Graph-Theoretic Intrinsic Reward: Guiding RL with Effective Resistance
Jatin Chauhan, Shivam Bhardwaj, Aditya Saibewar, Aditya Ramesh, Sadbhavana Babar, Manohar Kaul
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 effective-resistance intrinsic reward instead of GCPO | PPO agent · Navigation-Level-2 | success rate: 38.7% -> 55.5% | Improved |
| add effective-resistance intrinsic reward instead of best baseline | PPO agent · Navigation-Level-1 | success rate: 84.0% -> 99.6% | Improved |
| add effective-resistance intrinsic reward instead of best baseline | PPO agent · Building-Level-1 | success rate: 86.4% -> 99.2% | Improved |
| add effective-resistance intrinsic reward | PPO agent · Building-Level-2 | success rate: 38.8% -> 88.4% | Improved |
| add effective-resistance reward versus GCPO on reward | PPO agent · Navigation-Level-2 | median normalized reward: 0.0017 -> 0.0068 | Improved |
| add effective-resistance reward versus GCPO on reward | PPO agent · Building-Level-2 | median normalized reward: 0.0041 -> 0.0134 | Improved |
| add effective-resistance reward versus GCPO on steps | PPO agent · Navigation-Level-2 | median timesteps: 467 -> 242 | Improved |
| add effective-resistance reward versus GCPO on steps | PPO agent · Building-Level-2 | median timesteps: 384 -> 168 | Improved |
| add effective-resistance reward on easiest level | PPO agent · Navigation-Level-0 | median normalized reward: 0.0293 -> 0.0309 | No clear effect |
| add effective-resistance reward versus PPO for convergence | PPO agent · Building-Level-0 | loss plateau iteration: 1636 -> 576 | Improved |
| add entropy bonus to PPO | PPO · Fading environments | success rate | Mixed |
Closest papers by meaning
- Addressing Sparse-Rewards in RL with Scalable Hierarchical Novel Eigen Options (NeurIPS 2026 · similarity 0.90)
- DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning (NeurIPS 2025 · similarity 0.88)
- Action-Dependent Optimality-Preserving Reward Shaping (ICML 2025 · similarity 0.88)
- Adapting to Reward Progressivity via Spectral Reinforcement Learning (ICLR 2021 · similarity 0.88)
- Decoupling Exploration and Policy Optimization: Uncertainty Guided Tree Search for Hard Exploration (NeurIPS 2026 · similarity 0.87)
- The Distributional Reward Critic Framework for Reinforcement Learning Under Perturbed Rewards (AAAI 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.
