Research map / Reinforcement learning / Policy gradient and actor-critic
DAC: The Double Actor-Critic Architecture for Learning Options
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 DAC+PPO instead of OC or IOPG | option learning · DMControl transfer tasks | online training episode return | Helped |
| Use DAC+PPO instead of PPO | hierarchical policy learning · Swimmer | online training episode return | Helped |
| Use DAC+PPO instead of PPO | hierarchical policy learning · single-task learning, 3 of 4 tasks | online training episode return | No clear effect |
| Use DAC+PPO instead of AHP+PPO | hierarchical policy learning · single-task learning | online training episode return | No clear effect |
| Use DAC+PPO instead of OC or IOPG | option learning · first task in DMControl transfer pairs | online training episode return | Helped |
| Use DAC+PPO instead of PPO, PPOC, or AHP+PPO | option learning · first task in DMControl transfer pairs | online training episode return | No clear effect |
| Increase the number of options from 4 to 8 (ablation) | DAC+PPO · Walker2 transfer learning, second task | online training episode return | Helped |
| Reduce the number of options from 4 to 2 (ablation) | DAC+PPO · Walker2 transfer learning, second task | online training episode return | Hurt |
| Use DAC+PPO instead of DAC+A2C | option learning · single-task robot simulation tasks | online training episode return | Helped |
Closest papers by meaning
- Decoupled Policy Actor-Critic: Bridging Pessimism and Risk Awareness in Reinforcement Learning (AAAI 2025 · similarity 0.88)
- Regret Analysis of Average-Reward Unichain MDPs via an Actor-Critic Approach (NeurIPS 2025 · similarity 0.87)
- Mirror descent actor-critic methods for entropy regularised MDPs in general spaces: stability and convergence (NeurIPS 2026 · similarity 0.86)
- Diffusion Actor-Critic: Formulating Constrained Policy Iteration as Diffusion Noise Regression for Offline Reinforcement Learning (ICLR 2025 · similarity 0.86)
- Actor-Critics Can Achieve Optimal Sample Efficiency (ICML 2025 · similarity 0.86)
- Finite-Time Convergence and Sample Complexity of Actor-Critic Multi-Objective Reinforcement Learning (ICML 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.