reinforcement learning
Reinforcement learning is a type of machine learning where an agent learns to make decisions based on trial-and-error, by receiving feedback in the form of rewards or punishments for each action it takes, in order to maximize its cumulative reward over time.
Requires login.
Related Concepts (23)
- adaptive intelligence
- adaptive systems
- artifical intelligence
- artificial general intelligence
- artificial intelligence and robotics
- computational intelligence
- decision-making algorithms
- deep learning
- generative models
- human-level ai
- inference in neural networks
- long short-term memory (lstm)
- machine learning
- machine learning algorithms
- multi-agent systems
- neural network inference
- neural networks
- rapid autonomous development
- recurrent neural networks (rnn)
- self-attention
- superintelligent ai
- trial-and-error learning
- value learning in ai
Similar Concepts
- adversarial reinforcement learning
- deep reinforcement learning
- explainability of reinforcement learning
- inverse reinforcement learning
- iterative learning
- operant conditioning
- positive reinforcement
- quantum reinforcement learning
- reinforcement learning with attention
- reinforcement schedules
- reinforcement theory
- reward-based learning
- robot learning and adaptation
- robotic learning and adaptation
- robotic learning and improvement in gaming