Research map / Reinforcement learning / Visual and representation RL
Value-driven Hindsight Modelling
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 |
|---|---|---|---|
| Add HiMo to IMPALA | IMPALA · Portal Choice | performance | Helped |
| Add hindsight value functions to R2D2 | R2D2 · Atari 2600, 57 games | median human normalized score: 832.5% -> 965%; increase of 132.5% | Helped |
| Add hindsight value functions to R2D2 | R2D2 · Atari 2600, 57 games | mean human normalized score: 2818.5% -> 2980% | Helped |
| Add HiMo to IMPALA | IMPALA · Bowling | score | Helped |
| Use Hindsight Credit Assignment instead of vanilla IMPALA | IMPALA · Portal Choice | performance | No clear effect |
| Add HiMo to R2D2 | R2D2 · Atari 2600, representative training curves | training performance | Mixed |
Closest papers by meaning
- Foresee then Evaluate: Decomposing Value Estimation with Latent Future Prediction (AAAI 2021 · similarity 0.91)
- The Value-Improvement Path: Towards Better Representations for Reinforcement Learning (AAAI 2021 · similarity 0.90)
- Value-Consistent Representation Learning for Data-Efficient Reinforcement Learning (AAAI 2023 · similarity 0.89)
- Posterior Value Functions: Hindsight Baselines for Policy Gradient Methods (ICML 2021 · similarity 0.88)
- Calibrated Value-Aware Model Learning with Probabilistic Environment Models (ICML 2025 · similarity 0.87)
- Is Value Learning Really the Main Bottleneck in Offline RL? (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.