Research map / Reinforcement learning / Visual and representation RL
Advice-Guided Reinforcement Learning in a non-Markovian Environment
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 |
|---|---|---|---|
| Add advice {b} instead of using no advice (ablation) | AdvisoRL · Officeworld | training steps to convergence: 454.5 -> 307.5 | Helped |
| Add advice {bd} instead of using no advice (ablation) | AdvisoRL · Officeworld | training steps to convergence: 454.5 -> 189.0 | Helped |
| Add advice {bdb} instead of using no advice (ablation) | AdvisoRL · Officeworld | training steps to convergence: 454.5 -> 144.0 | Helped |
| Add advice {bdbg} instead of using no advice (ablation) | AdvisoRL · Officeworld | training steps to convergence: 454.5 -> 142.5 | Helped |
| Add advice {bdbg} instead of using no advice (ablation) | AdvisoRL · Officeworld | inference time: 149.0 -> 0.5 | Helped |
| Provide advice {g} alone rather than no advice (ablation) | AdvisoRL · Officeworld | cumulative inference time | Hurt |
| Provide advice {g} alone rather than no advice (ablation) | AdvisoRL · Officeworld | training steps to convergence | Helped |
| Add advice {a} to guide reward-machine inference (ablation) | AdvisoRL · Taxi | attained reward | Helped |
| Add advice {eabf} to guide reward-machine inference (ablation) | AdvisoRL · Taxi | attained reward | Helped |
Closest papers by meaning
- An Experimental Study of Advice in Sequential Decision-Making Under Uncertainty (AAAI 2018 · similarity 0.90)
- Teachable Reinforcement Learning via Advice Distillation (NeurIPS 2021 · similarity 0.90)
- Learning Safe Policies with Expert Guidance (NeurIPS 2018 · similarity 0.89)
- DUO: Diverse, Uncertain, On-Policy Query Generation and Selection for Reinforcement Learning from Human Feedback (AAAI 2025 · similarity 0.89)
- Reinforcement Learning with Lookahead Information (NeurIPS 2024 · similarity 0.88)
- Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward Inference (ICLR 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.