Research map / Reinforcement learning / Visual and representation RL
Reinforcement Learning with Stochastic Reward Machines
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 |
|---|---|---|---|
| Infer a stochastic reward machine instead of using classical reward-machine inference | Mining · Mining | cumulative reward | Helped |
| Infer a stochastic reward machine instead of averaging repeated trace samples before classical inference | Harvest · Harvest | cumulative reward | Helped |
| Use classical JIRP inference that does not explicitly model reward noise | Mining · Mining | cumulative reward | Hurt |
| Use classical JIRP inference that does not explicitly model reward noise | Harvest · Harvest | cumulative reward | Hurt |
| Apply SRMI in a non-stochastic reward setting | Mining · Mining, non-stochastic rewards | cumulative reward | No clear effect |
| Apply SRMI in a non-stochastic reward setting | Harvest · Harvest, non-stochastic rewards | cumulative reward | No clear effect |
Closest papers by meaning
- Efficient Reinforcement Learning in Probabilistic Reward Machines (AAAI 2025 · similarity 0.91)
- Learning Reward Machines for Partially Observable Reinforcement Learning (NeurIPS 2019 · similarity 0.89)
- Using Reward Machines for High-Level Task Specification and Decomposition in Reinforcement Learning (ICML 2018 · similarity 0.89)
- To the Max: Reinventing Reward in Reinforcement Learning (ICML 2024 · similarity 0.88)
- DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning (NeurIPS 2025 · similarity 0.86)
- Reward-Respecting Subtasks for Model-Based Reinforcement Learning (Abstract Reprint) (AAAI 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.