Research map / Reinforcement learning / Visual and representation RL
Machine versus Human Attention in Deep Reinforcement Learning Tasks
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 |
|---|---|---|---|
| Train PPO agents longer (attention evolves over training) | PPO · Human vs RL attention, Atari | CC: 0.170 -> 0.320 | Helped |
| Lower discount factor from 0.99 to 0.9 (ablation) | PPO · Seaquest | game score: 15% higher score | Helped |
| Lower discount factor from 0.99 to 0.9 (ablation) | PPO · Ms.Pac-Man | game score: 18% higher score | Helped |
| Raise discount factor to 0.9999 (ablation) | PPO · Atari games | game score | Hurt |
| Use discount factor 0.9 instead of 0.99 or 0.9999 (ablation) | PPO · Atari games | similarity to human attention (CC/KL) | Helped |
| Discount factor 0.9 vs default 0.99 (ablation) | PPO · Atari games overall | game score | Mixed |
Closest papers by meaning
- Attention Trajectories as a Diagnostic Axis for Deep Reinforcement Learning (NeurIPS 2026 · similarity 0.89)
- Focus-Then-Decide: Segmentation-Assisted Reinforcement Learning (AAAI 2024 · similarity 0.86)
- DMC-VB: A Benchmark for Representation Learning for Control with Visual Distractors (NeurIPS 2024 · similarity 0.86)
- The Surprising Ineffectiveness of Pre-Trained Visual Representations for Model-Based Reinforcement Learning (NeurIPS 2024 · similarity 0.86)
- DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization (ICLR 2024 · similarity 0.85)
- Perception-R1: Pioneering Perception Policy with Reinforcement Learning (NeurIPS 2025 · similarity 0.85)
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.