Research map / Bandits and online learning / RL theory and MDPs
Exploration Bonus for Regret Minimization in Discrete and Continuous Average Reward MDPs
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 SCAL+ exploration bonus instead of UCRL confidence sets when branching factor is large (Gamma=144) | SCAL+ · Garnet(200,3,144) | cumulative regret | Helped |
| use SCAL+ exploration bonus instead of UCRL confidence sets when branching factor is small (Gamma=5) | SCAL+ · Garnet(200,3,5) | cumulative regret | Hurt |
| use SCCAL+ instead of RVI Q-learning variants on continuous-state MDPs | SCCAL+ · RiverSwim and ShipSteering | cumulative reward stability | Mixed |
Closest papers by meaning
- Efficient Bias-Span-Constrained Exploration-Exploitation in Reinforcement Learning (ICML 2018 · similarity 0.91)
- Achieving Tractable Minimax Optimal Regret in Average Reward MDPs (NeurIPS 2024 · similarity 0.90)
- Efficient Exploration in Average-Reward Constrained Reinforcement Learning: Achieving Near-Optimal Regret With Posterior Sampling (ICML 2024 · similarity 0.89)
- Horizon-Free Regret for Linear Markov Decision Processes (ICLR 2024 · similarity 0.88)
- Regret Analysis of Policy Gradient Algorithm for Infinite Horizon Average Reward Markov Decision Processes (AAAI 2024 · similarity 0.88)
- Learning General Parameterized Policies for Infinite Horizon Average Reward Constrained MDPs via Primal-Dual Policy Gradient Algorithm (NeurIPS 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.