Psychology Wiki

Assessment | Biopsychology | Comparative | Cognitive | Developmental | Language | Individual differences | Personality | Philosophy | Social |
Methods | Statistics | Clinical | Educational | Industrial | Professional items | World psychology |

Cognitive Psychology: Attention · Decision making · Learning · Judgement · Memory · Motivation · Perception · Reasoning · Thinking  - Cognitive processes Cognition - Outline Index

Temporal difference learning is a prediction method. It has been mostly used for solving the reinforcement learning problem. "TD learning is a combination of Monte Carlo ideas and dynamic programming (DP) ideas." [2] TD resembles a Monte Carlo method because it learns by sampling the environment according to some policy. TD is related to dynamic programming techniques because it approximates its current estimate based on previously learned estimates (a process known as bootstrapping). The TD learning algorithm is related to the Temporal difference model of animal learning.

As a prediction method, TD learning takes into account the fact that subsequent predictions are often correlated in some sense. In standard supervised predictive learning, one only learns from actually observed values: A prediction is made, and when the observation is available, the prediction is adjusted to better match the observation. The core idea, as elucidated in [1], of TD learning is that we adjust predictions to match other, more accurate predictions, about the feature. This procedure is a form of bootstrapping as illustrated with the following example (taken from [1]):

Suppose you wish to predict the weather for Saturday and that you have some model that predicts Saturday's weather given the weather of each day in the week. In the standard case, you would wait until Saturday and then adjust all your models. However, when it is, for example Friday, you should have a pretty good idea of what the weather would be on Saturday - and thus be able to change, say, Monday's model before Saturday arrives.

Mathematically speaking, both in a standard and a TD approach, we would try to optimise some cost function, related to the error in our predictions of the expectation of some random variable, E[z]. However, while in the standard approach we in some sense assume E[z]=z (the actual observed value), in the TD approach we use a model. For the particular case of reinforcement learning, which is the major application of TD methods, z is the total return and E[z] is given by the Bellman equation of the return.

TD algorithm in neuroscience

The TD algorithm has also received attention in the field of Neuroscience. Researchers discovered that the firing rate of dopamine neurons in the ventral tegmental area (VTA) and substantia nigra (SNc) appear to mimic the error function in the algorithm [3]. The error function reports back the difference between the estimated reward at any given state or time step and the actual reward received. The larger the error function the larger the difference between the expected and actual reward. When this is paired with a stimulus that accurately reflects a future reward the error can be used to associate the stimulus with the future reward.

Dopamine cells appear to behave in a similar manner. In one experiment measurements of dopamine cells were made while training a monkey to associate a stimulus with the reward of juice [4]. Initially the dopamine cells increased firing rates when exposed to the juice, indicating a difference in expected and actual rewards. Over time this increase in firing back propagated to the earliest reliable stimulus for the reward. Once the monkey was fully trained the dopamine cells stopped firing. This mimics closely how the error function in TD is used for reinforcement learning.

The relationship between the model and potential neurological function has produced research attempting to use TD to explain many aspects of behavioral research [5]. It has also been used to study conditions such as schizophrenia or the consequences of pharmacological manipulations of dopamine on learning [6].


This article is in need of attention from a psychologist/academic expert on the subject.
Please help recruit one, or improve this page yourself if you are qualified.
This banner appears on articles that are weak and whose contents should be approached with academic caution.

Let be the reinforcement on time step t. Let be the correct prediction that is equal to discounted sum of all future reinforcement. The discounting is done by powers of factor of such that reinforcement at distant time step is less important.

This formula can be expanded

by changing the index of i to start from 0.

Thus, the reinforcement is the difference between the ideal prediction and the current prediction.

TD-Lambda is a learning algorithm invented by Richard Sutton based on earlier work on temporal difference learning by Arthur Samuel [2]. This algorithm was famously applied by Gerald Tesauro to create TD-Gammon, a program that can learn to play the game of backgammon nearly as good as expert human players. The lambda (λ) parameter here refers to the trace decay parameter, with 0 < λ < 1. Higher settings lead to longer lasting traces; that is, a larger proportion of credit from a reward can be given to more distal states and actions when λ is higher, with λ=1 producing parallel learning to Monte Carlo RL algorithms.

See also

External links


[0] Sutton, R.S., Barto A.G. (1990) Time Derivative Models of Pavlovian Reinforcement, Learning and Computational Neuroscience (available here).

[1] Richard Sutton. Learning to predict by the methods of temporal differences. Machine Learning 3:9-44. 1988. (A revised version is available on Richard Sutton's publication page)

[2] Richard Sutton and Andrew Barto. Reinforcement Learning. MIT Press, 1998. (available online)

[3] Schultz, W, Dayan, P & Montague, PR. 1997. A neural substrate of prediction and reward. Science 275:1593-1599.

[4] Schultz W. 1998. Predictive reward signal of dopamine neurons. J Neurophysiology 80:1–27.

[5] Dayan P. 2002. Motivated reinforcement learning. In: Ghahramani T, editor. Advances in neural information processing system, Cambridge, MA: MIT Press.

[6] Smith, A., Li, M., Becker, S. and Kapur, S. (2006), Dopamine, prediction error, and associative learning: a model-based account. Network: Computation in Neural Systems 17(1):61-84.

[7] Gerald Tesauro. Temporal Difference Learning and TD-Gammon. Communications of the ACM, March 1995 / Vol. 38, No. 3. (available at Temporal Difference Learning and TD-Gammon)

[8] Imran Ghory. Reinforcement Learning in Board Games.

Types of learning
Avoidance conditioning | Classical conditioning | Confidence-based learning | Discrimination learning | Emulation | Experiential learning | Escape conditioning | Incidental learning |Intentional learning | Latent learning | Maze learning | Mastery learning | Mnemonic learning | Nonassociative learning | Nonreversal shift learning | Nonsense syllable learning | Nonverbal learning | Observational learning | Omission training | Operant conditioning | Paired associate learning | Perceptual motor learning | Place conditioning | Probability learning | Rote learning | Reversal shift learning | Second-order conditioning | Sequential learning | Serial anticipation learning | Serial learning | Skill learning | Sidman avoidance conditioning | Social learning | Spatial learning | State dependent learning | Social learning theory | State-dependent learning | Trial and error learning | Verbal learning 
Concepts in learning theory
Chaining | Cognitive hypothesis testing | Conditioning | Conditioned responses | Conditioned stimulus | Conditioned suppression | Constant time delay | Counterconditioning | Covert conditioning | Counterconditioning | Delayed alternation | Delay reduction hypothesis | Discriminative response | Distributed practice |Extinction | Fast mapping | Gagné's hierarchy | Generalization (learning) | Generation effect (learning) | Habits | Habituation | Imitation (learning) | Implicit repetition | Interference (learning) | Interstimulus interval | Intermittent reinforcement | Latent inhibition | Learning schedules | Learning rate | Learning strategies | Massed practice | Modelling | Negative transfer | Overlearning | Practice | Premack principle | Preconditioning | Primacy effect | Primary reinforcement | Principles of learning | Prompting | Punishment | Recall (learning) | Recency effect | Recognition (learning) | Reconstruction (learning) | Reinforcement | Relearning | Rescorla-Wagner model | Response | Reinforcement | Secondary reinforcement | Sensitization | Serial position effect | Serial recall | Shaping | Stimulus | Reinforcement schedule | Spontaneous recovery | State dependent learning | Stimulus control | Stimulus generalization | Transfer of learning | Unconditioned responses | Unconditioned stimulus 
Animal learning
Cat learning | Dog learning  Rat learning 
Neuroanatomy of learning
Neurochemistry of learning
Adenylyl cyclase  
Learning in clinical settings
Applied Behavior Analysis | Behaviour therapy | Behaviour modification | Delay of gratification | CBT | Desensitization | Exposure Therapy | Exposure and response prevention | Flooding | Graded practice | Habituation | Learning disabilities | Reciprocal inhibition therapy | Systematic desensitization | Task analysis | Time out 
Learning in education
Adult learning | Cooperative learning | Constructionist learning | Experiential learning | Foreign language learning | Individualised instruction | Learning ability | Learning disabilities | Learning disorders | Learning Management | Learning styles | Learning theory (education) | Learning through play | School learning | Study habits 
Machine learning
Temporal difference learning | Q-learning 
Philosophical context of learning theory
Behaviourism | Connectionism | Constructivism | Functionalism | Logical positivism | Radical behaviourism 
Prominant workers in Learning Theory|-
Pavlov | Hull | Tolman | Skinner | Bandura | Thorndike | Skinner | Watson 
Category:Learning journals | Melioration theory 

This page uses Creative Commons Licensed content from Wikipedia (view authors).