Research map / Reinforcement learning / MDPs and planning
Adversarial Intrinsic Motivation for Reinforcement Learning
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 AIM-learned reward without task reward | HER + TD3 · Fetch Reach/Pick and Place/Push | success rate | Helped |
| add AIM reward on Fetch Slide | HER + TD3 · Fetch Slide | success rate | No clear effect |
| add AIM reward together with task reward (ablation) | AIM + HER · Fetch tasks | success rate | Helped |
| add RND bonus | R + HER · Fetch Push | learning speed | Helped |
| add RND bonus | R + HER · Fetch Pick and Place | success rate | Hurt |
| add MC distance regression reward | R + HER · Fetch Pick and Place | learning speed | Helped |
| add MC distance regression reward | R + HER · Fetch Push | learning speed | Hurt |
| add RND or MC reward | R + HER · Fetch Slide | success rate | Hurt |
| add GAIL relabeled reward | R + HER · Fetch tasks except Slide | success rate | Hurt |
| add SMiRL reward | R + HER · Fetch Reach | success rate | Hurt |
| use FAIRL reward | HER · Fetch tasks | success rate | Hurt |
| use AIM reward instead of sparse task reward | soft Q-learning · Grid world | goal reaching | Helped |
Closest papers by meaning
- Learn Goal-Conditioned Policy with Intrinsic Motivation for Deep Reinforcement Learning (AAAI 2022 · similarity 0.90)
- Learning with AMIGo: Adversarially Motivated Intrinsic Goals (ICLR 2021 · similarity 0.88)
- Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking (ICLR 2025 · similarity 0.86)
- Going Beyond Heuristics by Imposing Policy Improvement as a Constraint (NeurIPS 2024 · similarity 0.86)
- Offline Goal-conditioned Reinforcement Learning with Quasimetric Representations (NeurIPS 2025 · similarity 0.86)
- Uncertainty-Based Smooth Policy Regularisation for Reinforcement Learning with Few Demonstrations (NeurIPS 2025 · 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.