Temporal-difference reinforcement learning with distributed representations

Keyphrases

• Reinforcement Learning 100%
• Distributed Representation 100%
• Temporal Difference 100%
• Discount Factor 80%
• Dopamine 40%
• Exponential Discounting 40%
• Hyperbolic Discounting 40%
• Temporal Difference Algorithm 40%
• Behavioral Experiment 20%
• Dopaminergic Pathway 20%
• Conditioned Stimulus 20%
• Movement Initiation 20%
• Trace Conditioning 20%
• Error Signal 20%
• Taking Action 20%
• Equivalent State 20%
• Model Matching 20%
• World State 20%
• Transient Bursts 20%
• Delay Conditioning 20%
• Temporal Difference Model 20%
• Reinforcement Learning Model 20%
• Micro-agents 20%

Neuroscience

• Reinforcement Learning 100%
• Behavior (Neuroscience) 33%

Psychology

• Learning Model 100%