Research map / Reinforcement learning / MDPs and planning
Near Optimal Reward-Free 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 stationary-transition episodic MDP with soft-truncated planning and staged sampling (SSTP) | reward-free RL · episodic MDP, total reward bounded by 1 | sample complexity dependence on horizon H | Helped |
| Adopt the truncated-reward (total-bounded) assumption instead of per-step uniformly bounded reward | reward-free RL analysis · episodic MDP | generality of bound | No clear effect |
| Adapt SSTP to non-stationary episodic MDP (ablation) | reward-free RL · non-stationary episodic MDP | sample complexity | No clear effect |
Closest papers by meaning
- Reward-Free Exploration for Reinforcement Learning (ICML 2020 · similarity 0.94)
- On Reward-Free Reinforcement Learning with Linear Function Approximation (NeurIPS 2020 · similarity 0.91)
- On Reward-Free RL with Kernel and Neural Function Approximations: Single-Agent MDP and Markov Game (ICML 2021 · similarity 0.90)
- Towards Minimax Optimal Reward-free Reinforcement Learning in Linear MDPs (ICLR 2023 · similarity 0.90)
- Reward-Free Kernel-Based Reinforcement Learning (ICML 2024 · similarity 0.89)
- To the Max: Reinventing Reward in Reinforcement Learning (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.