Research map / Reinforcement learning / Visual and representation RL
Generalized Hindsight for Reinforcement Learning
Alexander Li, Lerrel Pinto, Pieter Abbeel
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 AIR task relabeling instead of no relabeling | SAC multi-task RL · PointTrajectory, PointReacher, Fetch, HalfCheetahMultiObjective, AntDirection | learning performance | Improved |
| Use Advantage relabeling instead of no relabeling | SAC multi-task RL · PointTrajectory, PointReacher, Fetch, HalfCheetahMultiObjective, AntDirection | learning performance | Improved |
| Select a few tasks by AIR rather than relabeling with random tasks | SAC multi-task RL · PointTrajectory, PointReacher, Fetch, HalfCheetahMultiObjective, AntDirection | learning performance | Improved |
| Use AIR instead of HER | SAC multi-task RL · PointReacher and Fetch | asymptotic performance | Improved |
| Replace AIR percentile-based task selection with Advantage relabeling (ablation) | Generalized Hindsight · PointTrajectory, PointReacher, Fetch, HalfCheetahMultiObjective, AntDirection | learning performance | No clear effect |
| Choose relabels by maximum trajectory reward instead of AIR percentile (ablation) | Generalized Hindsight · PointReacher relabeling fidelity | relabeling fidelity | Hurt |
Closest papers by meaning
- PIPER: Primitive-Informed Preference-based Hierarchical Reinforcement Learning via Hindsight Relabeling (ICML 2024 · similarity 0.87)
- Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning? A Theoretical Perspective (ICML 2024 · similarity 0.87)
- Null Counterfactual Factor Interactions for Goal-Conditioned Reinforcement Learning (ICLR 2025 · similarity 0.87)
- Hybrid Inverse Reinforcement Learning (ICML 2024 · similarity 0.87)
- Goal-Conditioned On-Policy Reinforcement Learning (NeurIPS 2024 · similarity 0.87)
- Prospective Hindsight: Self-Calibrating Reinforcement Learning via Prediction–Reality Gaps (NeurIPS 2026 · similarity 0.86)
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.
