Research map / Reinforcement learning / Imitation learning
Hybrid Reinforcement Learning with Expert State Sequences
Xiaoxiao Guo, Shiyu Chang, Mo Yu, Gerald Tesauro, Murray Campbell
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 |
|---|---|---|---|
| Combine A2C with imitation from inferred expert actions | Hybrid RL · Taxi | cumulative reward | Improved |
| Use the dual tensor action inference model instead of an MLP | Hybrid RL and behavioral cloning · Taxi | cumulative reward | Improved |
| Add RL reward signals to behavioral cloning | Hybrid RL · Taxi | cumulative reward | Improved |
| Use rank 1 instead of rank 2 for the tensor action inference model (ablation) | Hybrid RL · Taxi | cumulative reward | Hurt |
| Increase tensor rank from 2 to 4 (ablation) | Hybrid RL · Taxi | cumulative reward | No clear effect |
| Use the hybrid objective instead of pure A2C | Hybrid RL · Alien | game score | Improved |
| Use the hybrid objective instead of pure A2C | Hybrid RL · BeamRider | game score | Improved |
| Use the hybrid objective instead of pure A2C | Hybrid RL · Breakout | game score | Improved |
| Use the hybrid objective instead of pure A2C | Hybrid RL · MsPacman | game score | Improved |
| Use the hybrid objective instead of pure A2C | Hybrid RL · Pong | game score | Improved |
| Use the hybrid objective instead of pure A2C | Hybrid RL · Qbert | game score | Improved |
| Use the hybrid objective instead of pure A2C | Hybrid RL · Seaquest | game score | No clear effect |
Closest papers by meaning
- Beyond-Expert Performance with Limited Demonstrations: Efficient Imitation Learning with Double Exploration (ICLR 2025 · similarity 0.89)
- Random Expert Distillation: Imitation Learning via Expert Policy Support Estimation (ICML 2019 · similarity 0.89)
- Hierarchical Imitation and Reinforcement Learning (ICML 2018 · similarity 0.88)
- Hybrid Inverse Reinforcement Learning (ICML 2024 · similarity 0.88)
- Efficient Active Imitation Learning with Random Network Distillation (ICLR 2025 · similarity 0.87)
- Causal Imitation for Markov Decision Processes: a Partial Identification Approach (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.
