Research map / Reinforcement learning / Visual and representation RL
Curriculum-guided Hindsight Experience Replay
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 uniform hindsight goal sampling with curriculum-guided selection (CHER) | DDPG+HER · Shadow Dexterous Hand tasks (HandReach, Block, Egg, Pen) | median test success rate | Helped |
| replace uniform sampling with CHER | DDPG+HER · FetchReach | median test success rate | Helped |
| use energy-based trajectory prioritization (HEREBP) instead of HER | DDPG+HER · FetchReach | median test success rate | No clear effect |
| start with zero proximity weight (lambda0 = 0) instead of a nonzero initial value (ablation) | CHER · Hand environments | median test success rate | Hurt |
| use larger initial proximity weight lambda0 (ablation) | CHER · Hand environments | median test success rate | No clear effect |
| use a fixed lambda instead of exponentially increasing lambda curriculum (ablation) | CHER · Hand environments | median test success rate | Hurt |
Closest papers by meaning
- Hindsight Experience Replay (NeurIPS 2017 · similarity 0.90)
- Goal-Oriented Dialogue Policy Learning from Failures (AAAI 2019 · similarity 0.89)
- Exploration via Hindsight Goal Generation (NeurIPS 2019 · similarity 0.89)
- DHER: Hindsight Experience Replay for Dynamic Goals (ICLR 2019 · similarity 0.88)
- Cluster-Based Sampling in Hindsight Experience Replay for Robotic Tasks (Student Abstract) (AAAI 2024 · similarity 0.88)
- Goal-Conditioned On-Policy Reinforcement Learning (NeurIPS 2024 · 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.