Research map / Reinforcement learning / MDPs and planning
Uncertainty-Aware Action Advising for Deep Reinforcement Learning Agents
Felipe Leno Da Silva, Pablo Hernandez-Leal, Bilal Kartal, Matthew E. Taylor
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 |
|---|---|---|---|
| ask for advice by epistemic uncertainty (RCMP) instead of no advice | DQN agent · Gridworld | discounted reward | Improved |
| RCMP instead of random advice timing (ablation) | DQN agent · Gridworld | discounted reward | Improved |
| RCMP instead of importance advising (ablation) | DQN agent · Gridworld | discounted reward | No clear effect |
| RCMP instead of importance advising (ablation) | A3C agent · Pong | undiscounted reward | Improved |
| RCMP instead of no advice | A3C agent · Pong | undiscounted reward | Improved |
| use RCMP instead of random or importance advising (ablation) | advice budget · Gridworld and Pong | amount of advice used | Improved |
| use only 2 heads instead of more heads for uncertainty estimation (ablation) | RCMP uncertainty estimate · Gridworld | uncertainty curve smoothness | Hurt |
| increase number of heads to 100 (ablation) | RCMP uncertainty estimate · Gridworld | uncertainty curve smoothness | Mixed |
Closest papers by meaning
- Agent-Aware Training for Agent-Agnostic Action Advising in Deep Reinforcement Learning (AAAI 2025 · similarity 0.89)
- Sampling-Based Safe Reinforcement Learning (NeurIPS 2026 · similarity 0.87)
- Selective Uncertainty Propagation in Offline RL (AAAI 2025 · similarity 0.87)
- Learning Uncertainty-Aware Temporally-Extended Actions (AAAI 2024 · similarity 0.86)
- From Static Policies to Adaptive Priors in Offline Reinforcement Learning (NeurIPS 2026 · similarity 0.86)
- Test Where Decisions Matter: Importance-driven Testing for Deep Reinforcement Learning (NeurIPS 2024 · 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.
