Research map / Reinforcement learning / Visual and representation RL
Policy Continuation with Hindsight Inverse Dynamics
Hao Sun, Zhizhong Li, Xiaotong Liu, Bolei Zhou, Dahua Lin
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 PEHID instead of DDPG + HER | DDPG + HER baseline · FetchPush | success rate: 1.00 -> 0.95 | Hurt |
| Use PEHID instead of DDPG + HER | DDPG + HER baseline · FetchSlide | success rate: 0.30 -> 0.38 | Improved |
| Use PEHID instead of DDPG + HER | DDPG + HER baseline · FetchPickAndPlace | success rate: 0.60 -> 0.75 | Improved |
| Use PCHID with PPO | PPO · FetchReach | success rate | No clear effect |
| Add HER to PCHID | PCHID · FetchReach | success rate | Improved |
| Use 5-step HID with HER instead of 1-step HID | PCHID on GridWorld · GridWorld | rollout success rate | Improved |
| Augment DQN with HER | DQN · GridWorld | rollout success rate | Improved |
| Use joint training rather than output averaging or intrinsic reward | PCHID combined with other RL algorithms · GridWorld and FetchReach | performance | Improved |
Closest papers by meaning
- Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement (NeurIPS 2020 · similarity 0.89)
- Generalized Hindsight for Reinforcement Learning (NeurIPS 2020 · similarity 0.88)
- Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning? A Theoretical Perspective (ICML 2024 · similarity 0.87)
- Goal-Conditioned On-Policy Reinforcement Learning (NeurIPS 2024 · similarity 0.87)
- Hybrid Inverse Reinforcement Learning (ICML 2024 · similarity 0.86)
- Efficient Recurrent Off-Policy RL Requires a Context-Encoder-Specific Learning Rate (NeurIPS 2024 · similarity 0.85)
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.
