Research map / Learning theory and algorithms / Sample complexity
SBEED: Convergent Reinforcement Learning with Nonlinear Function Approximation
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 SBEED instead of TRPO, Dual AC, or DDPG | Continuous-control tasks: Pendulum-v0, InvertedDoublePendulum-v1, HalfCheetah-v1, Swimmer-v1, and Hopper-v1 · MuJoCo continuous control | average reward | Helped |
| Use an intermediate entropy-regularization coefficient λ rather than an extreme value (ablation) | SBEED · Swimmer-v1, stochastic transitions | average reward | Helped |
| Use an intermediate dual-function coefficient η rather than an extreme value (ablation) | SBEED · Swimmer-v1, stochastic transitions | average reward | Helped |
| Use an intermediate rollout length k rather than the tested shorter or longer alternatives (ablation) | SBEED · Swimmer-v1, stochastic transitions | average reward | Helped |
| Use DDPG instead of SBEED | Off-policy continuous-control tasks · HalfCheetah-v1 and Swimmer-v1 versus InvertedDoublePendulum-v1 and Hopper-v1 | average reward | Mixed |
Closest papers by meaning
- Natural Policy Gradient as Doubly Smoothed Policy Iteration: A Bellman-Operator Framework (NeurIPS 2026 · similarity 0.90)
- Computationally Efficient RL under Linear Bellman Completeness for Deterministic Dynamics (ICLR 2025 · similarity 0.89)
- Gradual Transition from Bellman Optimality Operator to Bellman Operator in Online Reinforcement Learning (ICML 2025 · similarity 0.88)
- Linear $Q$-Learning Does Not Diverge in $L^2$: Convergence Rates to a Bounded Set (ICML 2025 · similarity 0.88)
- Bellman Residual Minimization for Control: Geometry, Stationarity, and Convergence (NeurIPS 2026 · similarity 0.87)
- Parameterized Projected Bellman Operator (AAAI 2024 · 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.