Research map / Reinforcement learning / Policy gradient and actor-critic
Distributional Policy Evaluation: a Maximum Entropy approach to Representation Learning
Riccardo Zamboni, Alberto Maria Metelli, Marcello Restelli
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| increase boosting parameter beta from 3 to 450 | Distributional Max-Ent Progressive Factorization · GridWorld Block-MDP, N=50 and N=1000 | number of factorization steps: beta = 3 -> beta = 450 | Improved |
| increase sample size from N=50 to N=1000 at same beta | Distributional Max-Ent Progressive Factorization · GridWorld Block-MDP | number of factorization steps: N = 50 -> N = 1000 | Hurt |
| oracle factorization versus full singleton factorization | Distributional Max-Ent Policy Evaluation · GridWorld Block-MDP | KL divergence to true return distribution | No clear effect |
| full singleton factorization versus oracle factorization | Distributional Max-Ent Policy Evaluation · GridWorld Block-MDP | total bound Btot | Hurt |
| run progressive factorization beyond first split | Distributional Max-Ent Progressive Factorization · GridWorld Block-MDP | KL divergence | No clear effect |
| minimize the proxy objective J instead of no factorization | Distributional Max-Ent Progressive Factorization · GridWorld Block-MDP | KL divergence | Improved |
Closest papers by meaning
- DIME: Diffusion-Based Maximum Entropy Reinforcement Learning (ICML 2025 · similarity 0.88)
- Maximum Entropy Reinforcement Learning with Diffusion Policy (ICML 2025 · similarity 0.87)
- S$2$AC: Energy-Based Reinforcement Learning with Stein Soft Actor Critic (ICLR 2024 · similarity 0.87)
- Towards Principled Unsupervised Multi-Agent Reinforcement Learning (NeurIPS 2025 · similarity 0.87)
- SEMDICE: Off-policy State Entropy Maximization via Stationary Distribution Correction Estimation (ICLR 2025 · similarity 0.87)
- A Distributional Analogue to the Successor Representation (ICML 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.
