Research map / Reinforcement learning / Policy gradient and actor-critic
Improving Policy Gradient by Exploring Under-appreciated Rewards
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 |
|---|---|---|---|
| Replace MENT with UREX | policy-gradient LSTM · Copy | expected reward: 31.2 -> 31.2 | No clear effect |
| Replace MENT with UREX | policy-gradient LSTM · DuplicatedInput | expected reward: 15.4 -> 15.4 | No clear effect |
| Use UREX instead of MENT | policy-gradient LSTM · RepeatCopy | expected reward: 69.2 -> 81.1 | Helped |
| Use UREX instead of MENT | policy-gradient LSTM · Reverse | expected reward: 21.9 -> 27.2 | Helped |
| Use UREX instead of MENT | policy-gradient LSTM · ReversedAddition | expected reward: 8.7 -> 30.2 | Helped |
| Use UREX instead of MENT | policy-gradient LSTM · BinarySearch | expected reward: 8.6 -> 9.1 | Helped |
| Remove entropy regularization from the combined expected-reward and RAML objective (ablation) | UREX · algorithmic tasks | performance | Helped |
Closest papers by meaning
- DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning (NeurIPS 2025 · similarity 0.89)
- Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient Data Utilization (ICML 2024 · similarity 0.89)
- Generalizable Policy Improvement via Reinforcement Sampling (Student Abstract) (AAAI 2024 · similarity 0.89)
- MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization (ICLR 2025 · similarity 0.88)
- Beyond Optimism: Exploration With Partially Observable Rewards (NeurIPS 2024 · similarity 0.88)
- LLM-Explorer: A Plug-in Reinforcement Learning Policy Exploration Enhancement Driven by Large Language Models (NeurIPS 2025 · 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.