target agent
Country:
- North America > United States > Illinois > Cook County > Evanston (0.04)
- North America > United States > Indiana > Tippecanoe County > West Lafayette (0.04)
- North America > United States > Indiana > Tippecanoe County > Lafayette (0.04)
- (2 more...)
Industry:
- Leisure & Entertainment > Sports (1.00)
- Leisure & Entertainment > Games > Computer Games (0.94)
Technology:
- Information Technology > Artificial Intelligence > Machine Learning > Reinforcement Learning (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (1.00)
- Information Technology > Artificial Intelligence > Representation & Reasoning > Optimization (0.93)
- (3 more...)
Country:
- Europe > Switzerland > Zürich > Zürich (0.15)
- Europe > Belgium > Flanders > Flemish Brabant > Leuven (0.04)
- Africa > Central African Republic > Ombella-M'Poko > Bimbo (0.04)
Industry:
- Transportation > Ground > Road (0.95)
- Automobiles & Trucks (0.68)
Technology:
Country:
- North America > United States > Texas (0.04)
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.04)
- North America > United States > Virginia > Arlington County > Arlington (0.04)
- (5 more...)
Technology:
Country:
- North America > United States (0.04)
- Europe > Sweden > Skåne County > Malmö (0.04)
- Asia > China > Beijing > Beijing (0.04)
Industry:
- Information Technology (1.00)
- Leisure & Entertainment > Games > Computer Games (0.46)
Technology:
EDGE: Explaining Deep Reinforcement Learning Policies S1 Additional Technical Details
Note that these games are two-player games, we select the runner in You-Shall-Not-Pass and kicker in Kick-And-Defend as our target agent. Section 4 mentioned that we download a well-trained policy for each game.
Country:
- North America > United States > North Carolina > Wake County > Raleigh (0.04)
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.04)
Genre:
- Research Report > New Finding (0.47)
- Research Report > Experimental Study (0.47)
Industry:
- Education (0.34)
- Leisure & Entertainment > Games (0.34)
Technology:
EDGE: ExplainingDeepReinforcementLearning Policies
Deep reinforcement learning has shown great success in automatic policy learning for various sequential decision-making problems, such as training AI agents to defeat professional players in sophisticated games [74, 65, 24, 37] and controlling robots to accomplish complicated tasks [33, 38].
Technology: Information Technology > Artificial Intelligence > Machine Learning > Reinforcement Learning (1.00)
Country:
- Asia > Singapore (0.04)
- North America > United States (0.04)
- North America > Canada (0.04)
Technology:
AreAlphaZero-likeAgents Robustto AdversarialPerturbations?
However, searching the adversarial state is challenging due to the large, discrete, and non-differentiable search space.
Technology:
Country:
- Asia > Taiwan (0.04)
- Asia > Middle East > Jordan (0.04)