Research map / Reinforcement learning / Visual and representation RL
Counterfactual Data Augmentation using Locally Factored Dynamics
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 CoDA counterfactual data at 1:3 ratio to real data | TD3 batch RL · Pong, 25k samples | mean success (%): 13.2 -> 40.9 | Helped |
| add CoDA counterfactual data at 1:3 ratio to real data | TD3 batch RL · Pong, 250k samples | mean success (%): 78.2 -> 87.8 | Helped |
| add MBPO model-generated data instead of CoDA | TD3 batch RL · Pong, 25k samples | mean success (%): 13.2 -> 18.5 | Helped |
| add MBPO model-generated data | TD3 batch RL · Pong, 150k samples | mean success (%): 77.4 -> 72.6 | Hurt |
| increase CoDA ratio from 1:3 to 1:5 (ablation) | CoDA · Pong, 100k samples | mean success (%): 82.7 -> 76.6 | Hurt |
| add MBPO data on top of CoDA 1:3 (ablation) | CoDA · Pong, small data (25k) | mean success (%): 40.9 -> 46.8 | Helped |
| add MBPO data on top of CoDA 1:3 (ablation) | CoDA · Pong, large data (250k) | mean success (%): 87.8 -> 78.3 | Hurt |
| use CoDA with ground-truth mask versus learned mask (ablation) | CoDA · Spriteworld online RL | sample efficiency | Helped |
| use CoDA-generated data versus Dyna generated from same model | TD3 · Spriteworld online RL | sample efficiency | Helped |
| add CoDA to HER agent | HER · FetchPush and Slide2 | sample efficiency | Helped |
Closest papers by meaning
- Causal Action Influence Aware Counterfactual Data Augmentation (ICML 2024 · similarity 0.91)
- ACAMDA: Improving Data Efficiency in Reinforcement Learning through Guided Counterfactual Data Augmentation (AAAI 2024 · similarity 0.89)
- Modeling Unseen Environments with Language-guided Composable Causal Components in Reinforcement Learning (ICLR 2025 · similarity 0.87)
- Counterfactual Realizability (ICLR 2025 · similarity 0.86)
- Localized Dynamics-Aware Domain Adaption for Off-Dynamics Offline Reinforcement Learning (NeurIPS 2026 · similarity 0.86)
- Building Minimal and Reusable Causal State Abstractions for Reinforcement Learning (AAAI 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.