Research map / Reinforcement learning / Offline RL
Sample Efficient Offline RL via T-Symmetry Enforced Latent State-Stitching
Peng Cheng, Zhihao Wu, Jianxiong Li, Ziteng He, Haoran Xu, Wei Sun, Youfang Lin, Yunxin Liu, Xianyuan Zhan
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 |
|---|---|---|---|
| add latent forward and reverse dynamics to vanilla inverse dynamics module (ablation) | TS-IDM · Hopper-medium-expert (10k) | normalized score: 17.2 -> 35.5 | Improved |
| add ODE property loss (ablation) | TS-IDM · Hopper-medium-expert (10k) | normalized score: 35.5 -> 61.4 | Improved |
| add T-symmetry consistency loss (ablation) | TS-IDM · Hopper-medium-expert (10k) | normalized score: 61.4 -> 100.9 | Improved |
| add T-symmetry consistency loss (ablation) | TS-IDM · Halfcheetah-medium-expert (10k) | normalized score: 31.2 -> 40.7 | Improved |
| add T-symmetry consistency loss (ablation) | TS-IDM · Walker2d-medium-expert (10k) | normalized score: 58.5 -> 87.4 | Improved |
| add latent dynamics modules on Halfcheetah (ablation) | TS-IDM · Halfcheetah-medium-expert (10k) | normalized score: 29.7 -> 31.3 | No clear effect |
| add T-symmetry consistency loss (ablation) | TS-IDM · Antmaze-medium-diverse (100k) | normalized score: 34.1 -> 47.2 | Improved |
| add T-symmetry consistency loss (ablation) | TS-IDM · Antmaze-large-play (100k) | normalized score: 22.6 -> 47.3 | Improved |
| add T-symmetry regularizer in guide-policy optimization (ablation) | TELS · 10k datasets | normalized score | Improved |
| replace AE/VAE/contrastive representations with TS-IDM representation (ablation) | TELS · 10k datasets | normalized score | Improved |
| use shared weight 1 for all TS-IDM loss terms instead of 0.1 on T-symmetry (ablation) | TELS · Hopper-medium-expert (10k) | normalized score: 56.4 -> 100.9 | Improved |
| use beta 1 instead of 10 (ablation) | TELS · Hopper-medium-expert (10k) | normalized score: 37.6 -> 100.9 | Improved |
Closest papers by meaning
- A Clean Slate for Offline Reinforcement Learning (NeurIPS 2025 · similarity 0.89)
- Beyond OOD State Actions: Supported Cross-Domain Offline Reinforcement Learning (AAAI 2024 · similarity 0.89)
- Temporal Distance-aware Transition Augmentation for Offline Model-based Reinforcement Learning (ICML 2025 · similarity 0.89)
- Iteratively Refined Behavior Regularization for Offline Reinforcement Learning (NeurIPS 2024 · similarity 0.89)
- Offline RL with Observation Histories: Analyzing and Improving Sample Complexity (ICLR 2024 · similarity 0.89)
- Scaling Offline RL via Efficient and Expressive Shortcut Models (NeurIPS 2025 · similarity 0.89)
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.
