Research map / Reinforcement learning / Visual and representation RL
Generalizing Reinforcement Learning through Fusing Self-Supervised Learning into Intrinsic Motivation
Keyu Wu, Min Wu, Zhenghua Chen, Yuecong Xu, Xiaoli Li
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 the self-supervised-loss-derived intrinsic reward (ablation) | SIM on DMControl color hard tasks · color hard | average episode reward: 673±85 -> 803±33; 926±6 -> 940±2; 835±8 -> 841±13; 952±10 -> 953±7; 954±20 -> 960±6 | Improved |
| add the self-supervised-loss-derived intrinsic reward (ablation) | SIM on DMControl video easy tasks · video easy | average episode reward: 779±65 -> 861±33; 958±15 -> 963±5; 749±55 -> 770±18; 704±184 -> 820±135; 801±34 -> 815±38 | Mixed |
| add the self-supervised-loss-derived intrinsic reward (ablation) | SIM on DMControl video hard tasks · video hard | average episode reward: 438±104 -> 459±67; 810±36 -> 827±24; 390±50 -> 367±47; 237±165 -> 287±39; 353±18 -> 362±9 | Mixed |
| use SIM rather than the strongest listed baseline | SAC-based RL on DMControl color hard tasks · color hard | average episode reward: 692±68 -> 803±33; 893±12 -> 940±2; 805±28 -> 841±13; 949±19 -> 953±7; 803±72 -> 960±6 | Improved |
| use SIM rather than the strongest listed baseline | SAC-based RL on DMControl video easy tasks · video easy | average episode reward: 768±38 -> 861±33; 955±13 -> 963±5; 758±62 -> 770±18; 875±56 -> 820±135; 695±97 -> 815±38 | Mixed |
| use SIM rather than the strongest listed baseline | SAC-based RL on DMControl video hard tasks · video hard | average episode reward: 381±72 -> 459±67; 771±83 -> 827±24; 429±64 -> 367±47; 327±100 -> 287±39; 302±41 -> 362±9 | Mixed |
Closest papers by meaning
- Reinforcement Learning Guided Semi-Supervised Learning (NeurIPS 2024 · similarity 0.87)
- Foundation Policies with Hilbert Representations (ICML 2024 · similarity 0.87)
- Towards Generalizable Reinforcement Learning via Causality-Guided Self-Adaptive Representations (ICLR 2025 · similarity 0.86)
- An Optimal Discriminator Weighted Imitation Perspective for Reinforcement Learning (ICLR 2025 · similarity 0.86)
- On Generalization Across Environments In Multi-Objective Reinforcement Learning (ICLR 2025 · similarity 0.86)
- Closing the Gap between TD Learning and Supervised Learning - A Generalisation Point of View. (ICLR 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.
