Temporal Difference Reinforcement Learning Research Articles

Basis Function Adaptation in Temporal Difference Reinforcement Learning

Reinforcement Learning (RL) is an approach for solving complex multi-stage decision problems that fall under the general framework of Markov Decision Problems (MDPs), with possibly unknown parameters. Function approximation is essential for problems with a large state space, as it facilitates compact representation and enables generalization. Linear approximation architectures (where the adjustable parameters are the weights of pre-fixed basis functions) have recently gained prominence due to efficient algorithms and convergence guarantees. Nonetheless, an appropriate choice of basis function is important for the success of the algorithm. In the present paper we examine methods for adapting the basis function during the learning process in the context of evaluating the value function under a fixed control policy. Using the Bellman approximation error as an optimization criterion, we optimize the weights of the basis function while simultaneously adapting the (non-linear) basis function parameters. We present two algorithms for this problem. The first uses a gradient-based approach and the second applies the Cross Entropy method. The performance of the proposed algorithms is evaluated and compared in simulations.

Cocaine Signals Never Disappoint

The temporal difference reinforcement learning (TDRL) model provides a computational framework for describing how future rewards are valued, how current choices are made, and how differences between what is received and what is expected are fed back into updated calculations of future rewards. In TDRL, the difference signal between receipt and expectation is carried by neurons that use the transmitter dopamine. Redish (see the Perspective by Ahmed) applies this model and develops an explanation, in neural computational terms, for some aspects of behavior in the context of addictive substances. The key point is that cocaine induces, via pharmacologic pathways, a dopamine signal that does not accurately reflect or respond to the difference in actual and expected reward; cocaine is always valued as being more rewarding than originally thought. A. D. Redish, Addiction as a computational process gone awry. Science 306 , 1944-1947 (2004). [Abstract] [Full Text] S. H. Ahmed, Addiction as compulsive reward prediction. Science 306 , 1901-1902 (2004). [Summary] [Full Text]

Addiction as a Computational Process Gone Awry

Addictive drugs have been hypothesized to access the same neurophysiological mechanisms as natural learning systems. These natural learning systems can be modeled through temporal-difference reinforcement learning (TDRL), which requires a reward-error signal that has been hypothesized to be carried by dopamine. TDRL learns to predict reward by driving that reward-error signal to zero. By adding a noncompensable drug-induced dopamine increase to a TDRL model, a computational model of addiction is constructed that over-selects actions leading to drug receipt. The model provides an explanation for important aspects of the addiction literature and provides a theoretic view-point with which to address other aspects.

A topological reinforcement learning agent for navigation

This article proposes a reinforcement learning procedure for mobile robot navigation using a latent-like learning schema. Latent learning refers to learning that occurs in the absence of reinforcement signals and is not apparent until reinforcement is introduced. This concept considers that part of a task can be learned before the agent receives any indication of how to perform such a task. In the proposed topological reinforcement learning agent (TRLA), a topological map is used to perform the latent learning. The propagation of the reinforcement signal throughout the topological neighborhoods of the map permits the estimation of a value function which takes in average less trials and with less updatings per trial than six of the main temporal difference reinforcement learning algorithms: Q-learning, SARSA, Q(λ)-learning, SARSA(λ), Dyna-Q and fast Q(λ)-learning. The RL agents were tested in four different environments designed to consider a growing level of complexity in accomplishing navigation tasks. The tests suggested that the TRLA chooses shorter trajectories (in the number of steps) and/or requires less value function updatings in each trial than the other six reinforcement learning (RL) algorithms.

Modeling functions of striatal dopamine modulation in learning and planning.

The activity of midbrain dopamine neurons is strikingly similar to the reward prediction error of temporal difference reinforcement learning models. Experimental evidence and simulation studies suggest that dopamine neuron activity serves as an effective reinforcement signal for learning of sensorimotor associations in striatal matrisomes. In the current study, we simulate dopamine neuron activity with the extended temporal difference model of Pavlovian learning and examine the influences of this signal on medium spiny neurons in striatal matrisomes. The modeled influences include transient membrane effects of dopamine D(1) receptor activation, dopamine-dependent long-term adaptations of corticostriatal transmission, and effects of dopamine on rhythmic fluctuations of the membrane potential between an elevated "up-state" and a hyperpolarized "down-state". The most dominant activity in the striatal matrisomes is assumed to elicit behaviors via projections from the basal ganglia to the thalamus and the cortex. This "standard model" performs successfully when tested for sensorimotor learning and goal-directed behavior (planning). To investigate the contributions of our model assumptions to learning and planning, we test the performance of several model variants that lack one of these mechanisms. These simulations show that the adaptation of the dopamine-like signal is necessary for sensorimotor learning and planning. Sensorimotor learning requires dopamine-dependent long-term adaptation of corticostriatal transmission. Lack of dopamine-like novelty responses decreases the number of exploratory acts, which impairs planning capabilities. The model loses its planning capabilities if the dopamine-like signal is simulated with the original temporal difference model, because the original temporal difference model does not form novel associative chains. Transient membrane effects of the dopamine-like signal on striatal firing substantially shorten the reaction time in the planning task. The capability for planning is improved by influences of dopamine on the durations of membrane potential fluctuations and by manipulations that prolong the reaction time of the model. These results suggest that responses of dopamine neurons to conditioned stimuli contribute to sensorimotor reward learning, novelty responses of dopamine neurons stimulate exploration, and transient dopamine membrane effects are important for planning.