Research map / Reinforcement learning / Policy gradient and actor-critic
The Virtues of Laziness in Model-based RL: A Unified Objective and Algorithms
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 |
|---|---|---|---|
| Compute policy only on states sampled from the exploration distribution (LAMPS) instead of optimal planning in learned model | MBRL policy computation · Helicopter | LQR solver calls / computation | Helped |
| Value moment matching model loss (LAMPS-MM) instead of MLE model fitting | model fitting · WideTree | model selection probability over good model | Helped |
| Exploration-distribution-based policy learning (LAMPS) vs MBPO-SysID in model fitting | MBPO-based MBRL · Maze (D4RL PointMaze large, sparse reward) | return | Helped |
| Use exploration distribution for policy updates (LAMPS) on Mujoco locomotion (ablation) | MBPO-SysID · Mujoco locomotion | episodic return vs real-world samples | Helped |
| Doubling policy updates and model-rollout interactions (MBPO-SysID 2x) (ablation) | MBPO-SysID · Mujoco locomotion | episodic return | No clear effect |
| Value moment matching model fitting for LAMPS-MM on linear dynamical system | model fitting · Linear Dynamical System | convergence to expert performance | Helped |
Closest papers by meaning
- Mismatched No More: Joint Model-Policy Optimization for Model-Based RL (NeurIPS 2022 · similarity 0.91)
- When to Trust Your Model: Model-Based Policy Optimization (NeurIPS 2019 · similarity 0.90)
- Scalable Offline Model-Based RL with Action Chunks (ICLR 2026 · similarity 0.90)
- Model-based RL as a Minimalist Approach to Horizon-Free and Second-Order Bounds (ICLR 2025 · similarity 0.90)
- Tight Regret Bounds for Model-Based Reinforcement Learning with Greedy Policies (NeurIPS 2019 · similarity 0.90)
- Towards General-Purpose Model-Free Reinforcement Learning (ICLR 2025 · similarity 0.90)
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.