Research map / Reinforcement learning / Visual and representation RL
Reinforcement Learning with Perturbed Rewards
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 |
|---|---|---|---|
| Replace noisy rewards with estimated surrogate rewards | Q-Learning on CartPole · CartPole, ω = 0.7 | average score: 56.6 -> 172.1 | Helped |
| Replace noisy rewards with estimated surrogate rewards | DQN on CartPole · CartPole, ω = 0.7 | average score: 17.2 -> 189.3 | Helped |
| Replace noisy rewards with estimated surrogate rewards | DDPG on Pendulum · Pendulum, ω = 0.1 | average score: -1.03 -> -0.90 | Helped |
| Replace noisy rewards with known-matrix surrogate rewards | PPO · Five selected Atari games, ω = 0.3 | average score improvement: 119.8%↑ | Helped |
| Use estimated rather than known reward confusion matrices | PPO · Five selected Atari games, ω = 0.1 | average score improvement: 70.4%↑ -> 84.6%↑ | Helped |
| Use estimated rather than known reward confusion matrices | PPO · Five selected Atari games, ω = 0.3 | average score improvement: 119.8%↑ -> 80.8%↑ | Hurt |
| Add sample-mean variance reduction to surrogate rewards | Reward Robust RL on CartPole · CartPole | convergence speed or performance | Helped |
| Use sample-mean variance reduction without surrogate rewards | CartPole RL · CartPole | convergence to optimal policy | Hurt |
Closest papers by meaning
- The Distributional Reward Critic Framework for Reinforcement Learning Under Perturbed Rewards (AAAI 2025 · similarity 0.91)
- Learning to Explore with Parameter-Space Noise: A Deep Dive into Parameter-Space Noise for Reinforcement Learning with Verifiable Rewards (NeurIPS 2026 · similarity 0.88)
- To the Max: Reinventing Reward in Reinforcement Learning (ICML 2024 · similarity 0.88)
- The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret (ICML 2025 · similarity 0.87)
- Robustness Verification of Deep Reinforcement Learning Based Control Systems Using Reward Martingales (AAAI 2024 · similarity 0.87)
- Policy Filtration for RLHF to Mitigate Noise in Reward Models (ICML 2025 · similarity 0.87)
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.