Research map / Reinforcement learning / Policy gradient and actor-critic
Monte Carlo Augmented Actor-Critic for Sparse Reward Deep Reinforcement Learning from Suboptimal Demonstrations
Albert Wilcox, Ashwin Balakrishna, Jules Dedieu, Wyame Benslimane, Daniel S. Brown, Ken Goldberg
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 MCAC target to SAC (ablation) | SAC · Pointmass Navigation and Block Lifting | return / learning speed | Improved |
| add MCAC target to TD3 (ablation) | TD3 · all five domains | learning speed | Improved |
| add MCAC target to GQE (ablation) | GQE · Pointmass Navigation, Block Extraction, Sequential Pushing | learning speed | Improved |
| add MCAC target to GQE (ablation) | GQE · Door Opening and Block Lifting | return | No clear effect |
| add MCAC target to OEFD (ablation) | OEFD · Pointmass, Sequential Pushing, Block Lifting | learning efficiency | Improved |
| add MCAC target to OEFD (ablation) | OEFD · Block Extraction and Door Opening | return | No clear effect |
| add MCAC target to AWAC (ablation) | AWAC · Pointmass Navigation and Sequential Pushing | return | Improved |
| add MCAC target to AWAC (ablation) | AWAC · other 3 environments | return | No clear effect |
| add MCAC target to CQL (ablation) | CQL · all tasks | return | Improved |
| use MCAC when rewards are dense | MCAC · dense-reward tasks | return | Hurt |
| add MCAC without demonstrations (ablation) | SAC · all environments | return | No clear effect |
Closest papers by meaning
- Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning (ICLR 2025 · similarity 0.88)
- A Sharper Global Convergence Analysis for Average Reward Reinforcement Learning via an Actor-Critic Approach (ICML 2025 · similarity 0.87)
- Towards Global Optimality for Practical Average Reward Reinforcement Learning without Mixing Time Oracles (ICML 2024 · similarity 0.87)
- Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo (ICLR 2024 · similarity 0.87)
- Non-Asymptotic Analysis for Single-Loop (Natural) Actor-Critic with Compatible Function Approximation (ICML 2024 · similarity 0.87)
- ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages (ICML 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.
