Research map / Reinforcement learning / MDPs and planning
Combining Pessimism with Optimism for Robust and Efficient Model-Based Deep 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 |
|---|---|---|---|
| Use RH-UCRL instead of other robust deep RL algorithms | Mujoco tasks · Adversarial-robust setting | worst-case return | Helped |
| Use RH-UCRL instead of H-UCRL | Pendulum swing-up · Adversarial perturbations | performance | Helped |
| Use RH-UCRL instead of the non-robust baseline | Pendulum swing-up · Adversarial perturbations | robustness to worst-case perturbations | Helped |
| Explore both agent and adversary decision spaces (ablation) | RH-UCRL ablations · Adversarial-robust Mujoco tasks | worst-case return | Helped |
| Use RH-UCRL instead of non-robust algorithms | Robust policies · Non-robust evaluation | return | Helped |
Closest papers by meaning
- Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning (ICLR 2025 · similarity 0.91)
- Adversarial Diffusion for Robust Reinforcement Learning (NeurIPS 2025 · similarity 0.91)
- Improve Robustness of Reinforcement Learning against Observation Perturbations via l∞ Lipschitz Policy Networks (AAAI 2024 · similarity 0.90)
- Towards Robust Model-Based Reinforcement Learning Against Adversarial Corruption (ICML 2024 · similarity 0.90)
- Sampling-Based Safe Reinforcement Learning (NeurIPS 2026 · similarity 0.89)
- Enhancing Robustness in Deep Reinforcement Learning: A Lyapunov Exponent Approach (NeurIPS 2024 · similarity 0.89)
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.