Research map / Reinforcement learning / MDPs and planning
Unifying Task Specification in Reinforcement Learning
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 |
|---|---|---|---|
| transition-based soft termination (gamma=0.1 at pickup) instead of hard termination | taxi domain policy · Taxi domain | total reward (pickup and dropoff): 7.74 vs 7.73 | No clear effect |
| transition-based soft termination instead of hard termination | taxi domain policy · Taxi domain | added cost for turns: 5.54 vs 5.83 (lower is better) | Helped |
| state-based discounting without added hypothetical states instead of transition-based discounting | taxi domain policy · Taxi domain | total reward (pickup and dropoff): 0.00 vs 7.74 | Hurt |
| constant discount gamma_c=0.99 instead of transition-based termination | taxi domain policy · Taxi domain | total reward (pickup and dropoff): 0.01 vs 7.74 | Hurt |
| constant discount gamma_c=0.8 instead of transition-based termination | taxi domain policy · Taxi domain | total reward (pickup and dropoff): 7.34 vs 7.74 | Mixed |
| increasing lambda_c from 0 to 0.999 under episodic taxi discount (ablation) | contraction bound parameter s_D · Episodic taxi | s_D: 0.989 at 0.0 down to 0.086 at 0.999 (lower s_D tightens bound) | Helped |
Closest papers by meaning
- On the Expressivity of Objective-Specification Formalisms in Reinforcement Learning (ICLR 2024 · similarity 0.90)
- Task-agnostic Exploration in Reinforcement Learning (NeurIPS 2020 · similarity 0.90)
- Context-Sensitive Abstractions for Reinforcement Learning with Parameterized Actions (AAAI 2026 · similarity 0.89)
- Mitigating Partial Observability in Sequential Decision Processes via the Lambda Discrepancy (NeurIPS 2024 · similarity 0.88)
- Taming "data-hungry" reinforcement learning? Stability in continuous state-action spaces (NeurIPS 2024 · similarity 0.88)
- Inverting the Bellman Equation: From $Q$-Values to World Models (NeurIPS 2026 · similarity 0.88)
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.