原文传递
Evaluation of Using Deterministic Heuristics to Accelerate Reinforcement Learning.
| 题名： | Evaluation of Using Deterministic Heuristics to Accelerate Reinforcement Learning. |
| 作者： | Walton, G. M. |
| 关键词： | Artificial neural networks, Machine learning, Training, Artificial intelligence, Video games, Deep learning, Reinforcement learning, Iterative distillation, Deepmind, Atari learning environment, Convolutional neural networks, Back propagation, Heuristic |
| 摘要： | Neural networks frequently face long training times based on the corpus of data available to them. Reinforcement learning in particular can take a long time to attain satisfactory performance. Recent efforts to incorporate deterministic logical rules and physical laws into a neural network have met with promising results. From an existing baseline neural network that is designed to learn Pong strictly from pixel representation of the game board, this thesis adds a ball trajectory-based heuristic into the learning process and evaluates its performance. The evaluation initially shows game score improvements, but demonstrates a sharp score degradation after about 25,000 games. Another evaluation shows the heuristic incurs a training time increase of approximately 35%. More work remains for assessing the long-term viability of this approach. |
| 报告类型： | 科技报告 |
相关文献
- MODELING LEARNING AND EVOLUTIONARY ADAPTATION PROCESSES IN ACTIVITY SETTINGS: THEORY AND NUMERICAL SIMULATIONS.
- Predicting Pilot Behavior in Medium Scale Scenarios Using Game Theory and Reinforcement Learning.
- Scheduling for Urban Air Mobility using Safe Learning.
- Dynamic Spectrum Allocation in Urban Air Transportation System via Deep Reinforcement Learning.
- Development, Deployment, and Assessment of Activity-Based Transportation Courses.
- MODELING ROUTE CHOICE BEHAVIOR WITH STOCHASTIC LEARNING AUTOMATA.
检索历史
应用推荐
