To use all functions of this page, please activate cookies in your browser.
my.bionity.com
With an accout for my.bionity.com you can always see everything at a glance – and you can configure your own website and individual newsletter.
- My watch list
- My saved searches
- My saved topics
- My newsletter
Temporal difference learningTemporal 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]):
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. Additional recommended knowledge
TD algorithm in neuroscienceThe 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]. Mathematical BackgroundLet λt 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 γ 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.
See also
References[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. http://www.cs.bris.ac.uk/Publications/Papers/2000100.pdf [9] S. P. Meyn, 2007. Control Techniques for Complex Networks, Cambridge University Press, 2007. See final chapter, and appendix with abridged Meyn & Tweedie. |
|
This article is licensed under the GNU Free Documentation License. It uses material from the Wikipedia article "Temporal_difference_learning". A list of authors is available in Wikipedia. |