Research map / Reinforcement learning / Policy gradient and actor-critic
Regret Minimization Experience Replay in Off-Policy 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 ReMERT prioritization instead of baseline DQN replay | DQN · Enduro | score: 1185±100 -> 1303±258 | Helped |
| Use ReMERT prioritization instead of baseline DQN replay | DQN · KungFuMaster | score: 29147±7280 -> 35544±8432 | Helped |
| Use ReMERT prioritization instead of baseline DQN replay | DQN · Kangaroo | score: 6210±1007 -> 7572±1794 | Helped |
| Use ReMERT prioritization instead of baseline DQN replay | DQN · MsPacman | score: 3318±647 -> 3481±1351 | Helped |
| Use ReMERT prioritization instead of baseline DQN replay | DQN · Qbert | score: 13437±2537 -> 14511±1138 | Helped |
| Use ReMERT prioritization | SAC · MuJoCo and DMC tasks | performance | Mixed |
| Use ReMERN prioritization instead of DisCor | SAC · Meta-World | training speed | Helped |
| Use ReMERN prioritization instead of DisCor | SAC · Meta-World | asymptotic performance | Helped |
| Add TCE-based prioritization (ablation) | DQN · Gridworld | Q-value accuracy | Helped |
Closest papers by meaning
- Reliability-Adjusted Prioritized Experience Replay (ICLR 2026 · similarity 0.90)
- Prioritizing Samples in Reinforcement Learning with Reducible Loss (NeurIPS 2023 · similarity 0.89)
- Model-augmented Prioritized Experience Replay (ICLR 2022 · similarity 0.89)
- Demystifying the Paradox of Importance Sampling with an Estimated History-Dependent Behavior Policy in Off-Policy Evaluation (ICML 2025 · similarity 0.87)
- Prioritized Generative Replay (ICLR 2025 · similarity 0.87)
- Exploiting the Replay Memory Before Exploring the Environment: Enhancing Reinforcement Learning Through Empirical MDP Iteration (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.