Research map / Reinforcement learning / Visual and representation RL
Offline Goal-Conditioned Reinforcement Learning via $f$-Advantage Regression
Yecheng Jason Ma, Jason Yan, Dinesh Jayaraman, Osbert Bastani
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 |
|---|---|---|---|
| Use GoFAR instead of the strongest listed baseline | Offline GCRL · FetchPick | discounted return: 18.4 -> 19.7 | Improved |
| Use GoFAR instead of the strongest listed baseline | Offline GCRL · FetchPush | discounted return: 14.7 -> 18.2 | Improved |
| Use GoFAR instead of the strongest listed baseline | Offline GCRL · HandReach | discounted return: 5.97 -> 11.5 | Improved |
| Use GoFAR instead of the strongest listed baseline | Offline GCRL · D'ClawTurn | discounted return: 2.82 -> 9.34 | Improved |
| Use GoFAR instead of the strongest listed baseline | Offline GCRL · FetchSlide | discounted return: 2.73 -> 2.47 | Hurt |
| Add hindsight goal relabeling (ablation) | GoFAR · Offline GCRL tasks | discounted return | No clear effect |
| Remove hindsight goal relabeling (ablation) | GCSL and WGCSL · Offline GCRL tasks | discounted return | Hurt |
| Use sparse binary reward instead of the discriminator-derived reward (ablation) | GoFAR · Offline GCRL tasks | discounted return | Hurt |
| Replace chi-squared divergence with KL divergence (ablation) | GoFAR · Offline GCRL tasks | discounted return | Hurt |
| Use relabeling-free GoFAR rather than hindsight-relabeling baselines | Offline GCRL · Noisy FetchReach | discounted return | Improved |
| Add GoFAR planning to the low-level controller | Cross-robot hierarchical control · Cross-robot distant test goals | success rate: 19% -> 37% | Improved |
Closest papers by meaning
- Score Models for Offline Goal-Conditioned Reinforcement Learning (ICLR 2024 · similarity 0.91)
- Stitching Sub-trajectories with Conditional Diffusion Model for Goal-Conditioned Offline RL (AAAI 2024 · similarity 0.91)
- OGBench: Benchmarking Offline Goal-Conditioned RL (ICLR 2025 · similarity 0.90)
- Option-aware Temporally Abstracted Value for Offline Goal-Conditioned Reinforcement Learning (NeurIPS 2025 · similarity 0.90)
- Flattening Hierarchies with Policy Bootstrapping (NeurIPS 2025 · similarity 0.90)
- GO-DICE: Goal-Conditioned Option-Aware Offline Imitation Learning via Stationary Distribution Correction Estimation (AAAI 2024 · 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.
