reward function
Learning in Non-Cooperative Configurable Markov Decision Processes Giorgia Ramponi ETH AI Center Zurich, Switzerland gramponi@ethz.ch Alberto Maria Metelli Politecnico di Milano Milan, Italy
Reinforcement Learning agent and a configurator that can modify some environmental parameters to improve the agent's performance.
Country:
- Europe > Switzerland > Zürich > Zürich (0.86)
- Europe > Italy > Lombardy > Milan (0.40)
- North America > United States (0.04)
- (2 more...)
Technology:
- Information Technology > Artificial Intelligence > Representation & Reasoning > Agents (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Reinforcement Learning (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Learning Graphical Models > Undirected Networks > Markov Models (0.65)
Context Shift Reduction for Offline Meta-Reinforcement Learning Y unkai Gao
Offline meta-reinforcement learning (OMRL) utilizes pre-collected offline datasets to enhance the agent's generalization ability on unseen tasks.
Country:
Technology: Information Technology > Artificial Intelligence > Machine Learning > Reinforcement Learning (1.00)
Learning from Active Human Involvement through Proxy Value Propagation
Learning from active human involvement enables the human subject to actively intervene and demonstrate to the AI agent during training. The interaction and corrective feedback from human brings safety and AI alignment to the learning process.
Country:
- North America > United States > California > San Francisco County > San Francisco (0.14)
- North America > United States > California > Los Angeles County > Los Angeles (0.14)
- Europe > Sweden > Stockholm > Stockholm (0.04)
- (4 more...)
Industry:
- Education (1.00)
- Leisure & Entertainment > Games > Computer Games (0.93)
- Information Technology (0.93)
- Transportation > Ground > Road (0.67)
Technology:
- Information Technology > Artificial Intelligence > Robots (1.00)
- Information Technology > Artificial Intelligence > Representation & Reasoning > Agents (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Reinforcement Learning (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks (1.00)
Reinforcement learning from Human Feedback (RLHF) learns from preference signals, while standard Reinforcement Learning (RL) directly learns from reward
The latter case can be further reduced to adversarial MDP when preferences only depend on the final state.
Country:
- North America > United States (0.14)
- Asia > Middle East > Jordan (0.04)
- Europe > France (0.04)
- Europe > Austria (0.04)
Technology:
- Information Technology > Artificial Intelligence > Machine Learning > Reinforcement Learning (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (0.87)
- Information Technology > Artificial Intelligence > Machine Learning > Learning Graphical Models > Undirected Networks > Markov Models (0.68)
Country:
- North America > United States > Georgia > Fulton County > Atlanta (0.04)
- Europe > Hungary > Győr-Moson-Sopron County > Sopron (0.04)
Technology:
Country:
- Oceania > New Zealand > North Island > Auckland Region > Auckland (0.04)
- North America > United States > Illinois > Cook County > Chicago (0.04)
Genre:
- Questionnaire & Opinion Survey (0.94)
- Research Report > New Finding (0.94)
Industry:
- Leisure & Entertainment > Games (1.00)
- Education (0.68)
Technology:
Country:
- North America > United States > California > San Francisco County > San Francisco (0.14)
- Asia > Japan > Honshū > Chūgoku > Hiroshima Prefecture > Hiroshima (0.04)
- North America > United States > Louisiana > Orleans Parish > New Orleans (0.04)
- (4 more...)
Technology:
- Information Technology > Game Theory (1.00)
- Information Technology > Artificial Intelligence > Robots (1.00)
- Information Technology > Artificial Intelligence > Representation & Reasoning > Optimization (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Reinforcement Learning (1.00)
Country:
- North America > United States > Indiana (0.04)
- North America > Dominican Republic (0.04)
- Europe > Greece (0.04)
- (4 more...)
Technology:
Country:
- North America > United States > Minnesota > Hennepin County > Minneapolis (0.28)
- North America > United States > Texas > Brazos County > College Station (0.14)
- Asia > Middle East > Jordan (0.04)
- (3 more...)
Technology:
Country:
- North America > United States > Minnesota > Hennepin County > Minneapolis (0.28)
- North America > United States > Texas > Brazos County > College Station (0.14)
- Asia > Middle East > Jordan (0.04)
- (3 more...)
Technology: