Research map / Reinforcement learning / Visual and representation RL
Learning Reward Machines for Partially Observable 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 |
|---|---|---|---|
| Use learned reward machine memory (LRM+DDQN / LRM+DQRM) instead of LSTM-based A3C, ACER, PPO | RL agent · Cookie, Symbol and 2-keys domains | total reward per 10,000 training steps | Helped |
| Use learned reward machine memory instead of DDQN with last 10 observations | DDQN · Cookie, Symbol and 2-keys domains | total reward per 10,000 training steps | Helped |
| Use QRM-style experience sharing (LRM+DQRM) instead of plain DDQN policy learning on learned RM (ablation) | LRM · 2-keys domain | total reward | Helped |
| Use QRM-style experience sharing (LRM+DQRM) instead of DDQN (ablation) | LRM · Cookie and Symbol domains | learning speed and stability | Mixed |
Closest papers by meaning
- Efficient Reinforcement Learning in Probabilistic Reward Machines (AAAI 2025 · similarity 0.88)
- Contextual Pre-planning on Reward Machine Abstractions for Enhanced Transfer in Deep Reinforcement Learning (AAAI 2024 · similarity 0.87)
- Mitigating Partial Observability in Sequential Decision Processes via the Lambda Discrepancy (NeurIPS 2024 · similarity 0.87)
- To the Max: Reinventing Reward in Reinforcement Learning (ICML 2024 · similarity 0.87)
- Rethinking Transformers in Solving POMDPs (ICML 2024 · similarity 0.87)
- Reward Machines for Deep RL in Noisy and Uncertain Environments (NeurIPS 2024 · 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.