Research map / Reinforcement learning / Policy gradient and actor-critic
Regularized Anderson Acceleration for Off-Policy Deep Reinforcement Learning
Wenjie Shi, Shiji Song, Hui Wu, Ya-Chu Hsu, Cheng Wu, Gao Huang
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 RAA to Dueling-DQN | Dueling-DQN · Atari (Breakout, Qbert, SpaceInvaders) | learning speed / average return | Improved |
| add RAA to Dueling-DQN | Dueling-DQN · Enduro | learning speed | No clear effect |
| add RAA to TD3 | TD3 · MuJoCo (Ant, Hopper, Walker2d, HalfCheetah) | average return | Improved |
| add progressive update to RAA-TD3 (ablation) | RAA-TD3 · MuJoCo (4 tasks) | average return variance | Improved |
| add adaptive restart to RAA-TD3 (ablation) | RAA-TD3 · MuJoCo (4 tasks) | average return | Improved |
| increase regularization scale lambda from 0.001 to 0.1 (overlarge hurts) (ablation) | RAA-Dueling-DQN · Atari (4 games) | average return | Mixed |
| increase number of previous estimates m from 1 to 9 (ablation) | RAA-TD3 · Walker2d-v2 | convergence speed and final return | Improved |
| add RAA to TD3 across learning rates 0.01, 0.001, 0.0001 (ablation) | TD3 · Walker2d-v2 | average return | Improved |
Closest papers by meaning
- Towards General-Purpose Model-Free Reinforcement Learning (ICLR 2025 · similarity 0.88)
- Learning to Trust Bellman Updates: Selective State-Adaptive Regularization for Offline RL (ICML 2025 · similarity 0.87)
- Deep Policy Gradient Methods Without Batch Updates, Target Networks, or Replay Buffers (NeurIPS 2024 · similarity 0.86)
- Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL (ICML 2024 · similarity 0.86)
- Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimization (ICLR 2024 · similarity 0.86)
- Iteratively Refined Behavior Regularization for Offline Reinforcement Learning (NeurIPS 2024 · similarity 0.86)
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.
