Research map / Reinforcement learning / Offline RL
Supported Trust Region Optimization for Offline Reinforcement Learning
Yixiu Mao, Hongchang Zhang, Chen Chen, Yi Xu, Xiangyang Ji
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 |
|---|---|---|---|
| Replace a Gaussian behavior density estimator with a conditional VAE (ablation) | STR · D4RL tasks, especially hopper-random | normalized score | Mixed |
| Initialize the policy randomly instead of from the pretrained behavior policy (ablation) | STR · D4RL tasks, especially hopper-expert and hopper-medium-expert | normalized score | Mixed |
| Use vanilla importance sampling instead of self-normalized importance sampling (ablation) | STR · D4RL tasks | normalized score | Hurt |
| Use a support constraint rather than a density constraint toward behavior | STR versus prior EAWBC methods · halfcheetah-random | normalized score | Improved |
| Use supported trust-region updates with importance sampling from the dataset | STR versus offline baselines · AntMaze tasks | normalized score | Improved |
| Use supported trust-region updates rather than AWAC updates | STR versus AWAC · hopper-medium, hopper-medium-replay, walker2d-medium-replay | normalized score | Mixed |
| Use STR policy iterations with approximate Q and sampling error | STR · Offline policy updates | safe policy improvement | Improved |
Closest papers by meaning
- Learning to Constrain Policy Optimization with Virtual Trust Region (NeurIPS 2022 · similarity 0.92)
- An Implicit Trust Region Approach to Behavior Regularized Offline Reinforcement Learning (AAAI 2024 · similarity 0.90)
- Embedding Safety into RL: A New Take on Trust Region Methods (ICML 2025 · similarity 0.89)
- Trust Region Q Adjoint Matching (NeurIPS 2026 · similarity 0.88)
- Adaptive Neighborhood-Constrained Q Learning for Offline Reinforcement Learning (NeurIPS 2025 · similarity 0.87)
- Online Optimization for Offline Safe Reinforcement Learning (NeurIPS 2025 · 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.
