Research map / Reinforcement learning / Visual and representation RL
Deep Reinforcement and InfoMax Learning
Bogdan Mazoure, Remi Tachet des Combes, Thang Long Doan, Philip Bachman, R Devon Hjelm
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 |
|---|---|---|---|
| add DRIML auxiliary DIM objective with adaptive lookahead | C51 · Procgen 16 games | normalized score: 1.0 -> 1.9 | Improved |
| use fixed lookahead with data augmentation (DRIML-fix) instead of C51 | C51 · Procgen 16 games | normalized score: 1.0 -> 1.48 | Improved |
| adaptive lookahead k via non-homogeneous geometric sampling instead of random k (ablation) | DRIML · Procgen 16 games | normalized score: 0.92 -> 1.9 | Improved |
| condition DIM prediction on action (ablation) | DRIML · Procgen 16 games | normalized score: 0.59 -> 1.9 | Improved |
| use DRIML-ada instead of C51 per game | C51 · Procgen individual games | average return: bigfish 1.33 -> 4.45; coinrun 29.7 -> 22.88 | Mixed |
| use DRIML-ada instead of CURL | CURL · Procgen 16 games | normalized score: 0.52 -> 1.9 | Improved |
| lookahead k=5 instead of k=1 (ablation) | DRIML-noact · Procgen fruitbot, jumper, caveflyer | average return: fruitbot 0.714 -> 5.425; caveflyer 8.263 -> 5.925 | Mixed |
| add DRIML auxiliary loss to C51 | C51 · Continual Ms. PacMan (changing lethal ghost) | average training reward | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- CURL — CURL: Contrastive Unsupervised Representations for Reinforcement Learning (ICML 2020) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Bridging State and History Representations: Understanding Self-Predictive RL (ICLR 2024 · similarity 0.86)
- Predictive Coding Enhances Meta-RL To Achieve Interpretable Bayes-Optimal Belief Representation Under Partial Observability (NeurIPS 2025 · similarity 0.86)
- Provable Partially Observable Reinforcement Learning with Privileged Information (NeurIPS 2024 · similarity 0.86)
- Mitigating Partial Observability in Sequential Decision Processes via the Lambda Discrepancy (NeurIPS 2024 · similarity 0.85)
- Skill-aware Mutual Information Optimisation for Zero-shot Generalisation in Reinforcement Learning (NeurIPS 2024 · similarity 0.85)
- The Ladder in Chaos: Improving Policy Learning by Harnessing the Parameter Evolving Path in A Low-dimensional Space (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.
