Research map / Reinforcement learning / Visual and representation RL
Adaptive Interest for Emphatic Reinforcement Learning
Martin Klissarov, Rasool Fakoor, Jonas Mueller, Kavosh Asadi, Taesup Kim, Alex Smola
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 |
|---|---|---|---|
| adapt the interest function with meta-gradients (MINT) instead of fixed interest | emphatic TD / PPO · H4R8T off-policy evaluation | MSVE | Improved |
| use TD-error-based adaptive interest instead of meta-gradient interest | emphatic TD · 4R8T and H4R8T off-policy evaluation | MSVE | No clear effect |
| add adaptive interest to ETDLB | ETDLB · 4R8T off-policy evaluation | convergence speed | Improved |
| add MINT on top of PPO | PPO · MinAtar (5 games) | reward | Improved |
| use TD-error interest in control | PPO · MuJoCo | reward | No clear effect |
| add MINT interest function to PPO | PPO · MuJoCo | reward | Improved |
| add hypergradient descent learning-rate adaptation | PPO · MuJoCo | reward | No clear effect |
| transfer learned interest function to new task | actor-critic · FourRoomsTransfer | learning speed | Improved |
| transfer meta-learned intrinsic reward instead of interest | actor-critic · FourRoomsTransfer | learning speed | No clear effect |
Closest papers by meaning
- Discovering Temporally-Aware Reinforcement Learning Algorithms (ICLR 2024 · similarity 0.88)
- Can Learned Optimization Make Reinforcement Learning Less Difficult? (NeurIPS 2024 · similarity 0.87)
- The Power of Resets in Online Reinforcement Learning (NeurIPS 2024 · similarity 0.87)
- Exploiting the Replay Memory Before Exploring the Environment: Enhancing Reinforcement Learning Through Empirical MDP Iteration (NeurIPS 2024 · similarity 0.87)
- Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning? A Theoretical Perspective (ICML 2024 · similarity 0.86)
- A Geometric Perspective on Reward Function Updates in Inverse Reinforcement Learning (NeurIPS 2026 · 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.
