Research map / Reinforcement learning / MDPs and planning
Reinforcement Learning Can Be More Efficient with Multiple Rewards
Christoph Dann, Yishay Mansour, Mehryar Mohri
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 multiple reward functions (max operator, action elimination) instead of a single reward | multi-armed bandit action elimination · Multi-armed bandits, theory (Theorem 2) | regret bound per action scaling | Improved |
| Add multiple reward functions in tabular MDP action elimination | multi-reward AMB-style action elimination · Tabular MDPs, theory (Theorem 3 vs single-reward Xu et al. 2021 bound) | regret bound scaling per state-action pair | Improved |
| Use multiple rewards with n=m reward functions in the MDP example vs single reward (ablation) | multi-reward RL on constructed MDP · Simulated MDP with H=n (Figure 2) | cumulative regret on reward r1 | Improved |
| Add second reward function in two-reward bandit example (Example 3) (ablation) | multi-armed bandit action elimination · Bandit Example 3 (theory) | regret bound: decreases regret bound by a ln(T) factor | Improved |
| Use multi-reward operator choice (mean/CVaR) instead of max when rewards disagree | multi-armed bandit action elimination · Theory (Theorem 1) | operator regret | Mixed |
| Model selection over the operator (max_i or CVaR family) adaptively | multi-armed bandit action elimination · Two-instance lower bound (theory) | regret | No clear effect |
Closest papers by meaning
- To the Max: Reinventing Reward in Reinforcement Learning (ICML 2024 · similarity 0.88)
- Multi-Reward Best Policy Identification (NeurIPS 2024 · similarity 0.88)
- The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret (ICML 2025 · similarity 0.88)
- Adaptive Exploration for Multi-Reward Multi-Policy Evaluation (ICML 2025 · similarity 0.88)
- Causal Bandits: The Pareto Optimal Frontier of Adaptivity, a Reduction to Linear Bandits, and Limitations around Unknown Marginals (ICML 2024 · similarity 0.88)
- Near-Optimal Reinforcement Learning with Self-Play under Adaptivity Constraints (ICML 2024 · similarity 0.88)
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.
