Tag Archives: Reinforcement Learning

Interesting review of pshycological motivation and the role of RL in studying it

Randall C. O’Reilly, Unraveling the Mysteries of Motivation, Trends in Cognitive Sciences, Volume 24, Issue 6, 2020, Pages 425-434, DOI: 10.1016/j.tics.2020.03.001.

Motivation plays a central role in human behavior and cognition but is not well captured by widely used artificial intelligence (AI) and computational modeling frameworks. This Opinion article addresses two central questions regarding the nature of motivation: what are the nature and dynamics of the internal goals that drive our motivational system and how can this system be sufficiently flexible to support our ability to rapidly adapt to novel situations, tasks, etc.? In reviewing existing systems and neuroscience research and theorizing on these questions, a wealth of insights to constrain the development of computational models of motivation can be found.

On rewards and values when the RL theory is applied to human brain

Keno Juechems, Christopher Summerfield, Where Does Value Come From?. Trends in Cognitive Sciences, Volume 23, Issue 10, 2019, Pages 836-850, DOI: 10.1016/j.tics.2019.07.012.

The computational framework of reinforcement learning (RL) has allowed us to both understand biological brains and build successful artificial agents. However, in this opinion, we highlight open challenges for RL as a model of animal behaviour in natural environments. We ask how the external reward function is designed for biological systems, and how we can account for the context sensitivity of valuation. We summarise both old and new theories proposing that animals track current and desired internal states and seek to minimise the distance to a goal across multiple value dimensions. We suggest that this framework readily accounts for canonical phenomena observed in the fields of psychology, behavioural ecology, and economics, and recent findings from brain-imaging studies of value-guided decision-making.

Human interaction with the RL process

Celemin, C., Ruiz-del-Solar, J. & Kober, A fast hybrid reinforcement learning framework with human corrective feedback, Auton Robot (2019) 43: 1173, DOI: 10.1007/s10514-018-9786-6.

Reinforcement Learning agents can be supported by feedback from human teachers in the learning loop that guides the learning process. In this work we propose two hybrid strategies of Policy Search Reinforcement Learning and Interactive Machine Learning that benefit from both sources of information, the cost function and the human corrective feedback, for accelerating the convergence and improving the final performance of the learning process. Experiments with simulated and real systems of balancing tasks and a 3 DoF robot arm validate the advantages of the proposed learning strategies: (i) they speed up the convergence of the learning process between 3 and 30 times, saving considerable time during the agent adaptation, and (ii) they allow including non-expert feedback because they have low sensibility to erroneous human advice.

On how attention, modelled by bayesian inference (for category learning), can structure the way reinforcement learning works

Angela Radulescu, Yael Niv, Ian Ballard, Holistic Reinforcement Learning: The Role of Structure and Attention, Trends in Cognitive Sciences, Volume 23, Issue 4, 2019, Pages 278-292, DOI: 10.1016/j.tics.2019.01.010.

Compact representations of the environment allow humans to behave efficiently in a complex world. Reinforcement learning models capture many behavioral and neural effects but do not explain recent findings showing that structure in the environment influences learning. In parallel, Bayesian cognitive models predict how humans learn structured knowledge but do not have a clear neurobiological implementation. We propose an integration of these two model classes in which structured knowledge learned via approximate Bayesian inference acts as a source of selective attention. In turn, selective attention biases reinforcement learning towards relevant dimensions of the environment. An understanding of structure learning will help to resolve the fundamental challenge in decision science: explaining why people make the decisions they do.

On how value of actions (in the RL sense) can be coded in the brain

Rory J. Bufacchi, Gian Domenico Iannetti, The Value of Actions, in Time and Space, Trends in Cognitive Sciences, Volume 23, Issue 4, 2019, Pages 270-271, DOI: 10.1016/j.tics.2019.01.011.

This value-output function can be a neural network, in which case the assumptions about the future are stored in the precise network configuration. The values that such a network outputs, or at least the intermediate steps necessary for calculating the final values, are the ‘action relevances’ we mention in our original paper (in the case of the brain, the inputs to such a value-calculating network should be state estimators, which likely include activity coming from the ventral stream, frontal areas, and limbic regions [3]). Our claim was thus that PPS-related measures reflect the instantaneous value of particular types of actions, and not that PPS measures explicitly reflect the value of any possible action at any given time (i.e., for any possible state): PPS measures reflect the instantaneous output of a function rather than the infinite array of values that the output of this function could take. We might have contributed to this misunderstanding when claiming that a field is ‘a quantity that has a magnitude for each point in space and time’. We should have clarified that the magnitude of a PPS measure can be seen as a specific sample from a field in the here and now rather than as a database containing all possible field values.

RL and Inverse RL based on MDPs for autonomous vehicles, and a nice historical review of the topic of a.v.

Changxi You, Jianbo Lu, Dimitar Filev, Panagiotis Tsiotras, Advanced planning for autonomous vehicles using reinforcement learning and deep inverse reinforcement learning, Robotics and Autonomous Systems, Volume 114, 2019, Pages 1-18 DOI: 10.1016/j.robot.2019.01.003.

Autonomous vehicles promise to improve traffic safety while, at the same time, increase fuel efficiency and reduce congestion. They represent the main trend in future intelligent transportation systems. This paper concentrates on the planning problem of autonomous vehicles in traffic. We model the interaction between the autonomous vehicle and the environment as a stochastic Markov decision process (MDP) and consider the driving style of an expert driver as the target to be learned. The road geometry is taken into consideration in the MDP model in order to incorporate more diverse driving styles. The desired, expert-like driving behavior of the autonomous vehicle is obtained as follows: First, we design the reward function of the corresponding MDP and determine the optimal driving strategy for the autonomous vehicle using reinforcement learning techniques. Second, we collect a number of demonstrations from an expert driver and learn the optimal driving strategy based on data using inverse reinforcement learning. The unknown reward function of the expert driver is approximated using a deep neural-network (DNN). We clarify and validate the application of the maximum entropy principle (MEP) to learn the DNN reward function, and provide the necessary derivations for using the maximum entropy principle to learn a parameterized feature (reward) function. Simulated results demonstrate the desired driving behaviors of an autonomous vehicle using both the reinforcement learning and inverse reinforcement learning techniques.

A new model of reinforcement learning based on the human brain that copes with continuous spaces through continuous rewards, with a short but nice state-of-the-art of RL applied to large, continuous spaces

Feifei Zhao, Yi Zeng, Guixiang Wang, Jun Bai, Bo Xu, A Brain-Inspired Decision Making Model Based on Top-Down Biasing of Prefrontal Cortex to Basal Ganglia and Its Application in Autonomous UAV Explorations, Cognitive Computation, Volume 10, Issue 2, pp 296–306, DOI: 10.1007/s12559-017-9511-3.

Decision making is a fundamental ability for intelligent agents (e.g., humanoid robots and unmanned aerial vehicles). During decision making process, agents can improve the strategy for interacting with the dynamic environment through reinforcement learning. Many state-of-the-art reinforcement learning models deal with relatively smaller number of state-action pairs, and the states are preferably discrete, such as Q-learning and Actor-Critic algorithms. While in practice, in many scenario, the states are continuous and hard to be properly discretized. Better autonomous decision making methods need to be proposed to handle these problems. Inspired by the mechanism of decision making in human brain, we propose a general computational model, named as prefrontal cortex-basal ganglia (PFC-BG) algorithm. The proposed model is inspired by the biological reinforcement learning pathway and mechanisms from the following perspectives: (1) Dopamine signals continuously update reward-relevant information for both basal ganglia and working memory in prefrontal cortex. (2) We maintain the contextual reward information in working memory. This has a top-down biasing effect on reinforcement learning in basal ganglia. The proposed model separates the continuous states into smaller distinguishable states, and introduces continuous reward function for each state to obtain reward information at different time. To verify the performance of our model, we apply it to many UAV decision making experiments, such as avoiding obstacles and flying through window and door, and the experiments support the effectiveness of the model. Compared with traditional Q-learning and Actor-Critic algorithms, the proposed model is more biologically inspired, and more accurate and faster to make decision.

A very interesting analysis on how reinforcement learning depends on time, both for MDPs and for the psychological basis of RL in the human brain

Elijah A. Petter, Samuel J. Gershman, Warren H. Meck, Integrating Models of Interval Timing and Reinforcement Learning, Trends in Cognitive Sciences, Volume 22, Issue 10, 2018, Pages 911-922 DOI: 10.1016/j.tics.2018.08.004.

We present an integrated view of interval timing and reinforcement learning (RL) in the brain. The computational goal of RL is to maximize future rewards, and this depends crucially on a representation of time. Different RL systems in the brain process time in distinct ways. A model-based system learns ‘what happens when’, employing this internal model to generate action plans, while a model-free system learns to predict reward directly from a set of temporal basis functions. We describe how these systems are subserved by a computational division of labor between several brain regions, with a focus on the basal ganglia and the hippocampus, as well as how these regions are influenced by the neuromodulator dopamine.

Some quotes beyond the abstract:

The Markov assumption also makes explicit the requirements for temporal representation. All temporal dynamics must be captured by the state-transition function, which means that the state representation must encode the time-invariant structure of the environment.

An interesting model of Basal Ganglia that performs similarly to Q learning when applied to a robot

Y. Zeng, G. Wang and B. Xu, A Basal Ganglia Network Centric Reinforcement Learning Model and Its Application in Unmanned Aerial Vehicle, IEEE Transactions on Cognitive and Developmental Systems, vol. 10, no. 2, pp. 290-303 DOI: 10.1109/TCDS.2017.2649564.

Reinforcement learning brings flexibility and generality for machine learning, while most of them are mathematical optimization driven approaches, and lack of cognitive and neural evidence. In order to provide a more cognitive and neural mechanisms driven foundation and validate its applicability in complex task, we develop a basal ganglia (BG) network centric reinforcement learning model. Compared to existing work on modeling BG, this paper is unique from the following perspectives: 1) the orbitofrontal cortex (OFC) is taken into consideration. OFC is critical in decision making because of its responsibility for reward representation and is critical in controlling the learning process, while most of the BG centric models do not include OFC; 2) to compensate the inaccurate memory of numeric values, precise encoding is proposed to enable working memory system remember important values during the learning process. The method combines vector convolution and the idea of storage by digit bit and is efficient for accurate value storage; and 3) for information coding, the Hodgkin-Huxley model is used to obtain a more biological plausible description of action potential with plenty of ionic activities. To validate the effectiveness of the proposed model, we apply the model to the unmanned aerial vehicle (UAV) autonomous learning process in a 3-D environment. Experimental results show that our model is able to give the UAV the ability of free exploration in the environment and has comparable learning speed as the Q learning algorithm, while the major advances for our model is that it is with solid cognitive and neural basis.

Relation between optimization and reinforcement learning

Megumi Miyashita, Shiro Yano, Toshiyuki Kondo Mirror descent search and its acceleration, Robotics and Autonomous Systems, Volume 106, 2018, Pages 107-116 DOI: 10.1016/j.robot.2018.04.009.

In recent years, attention has been focused on the relationship between black-box optimization problem and reinforcement learning problem. In this research, we propose the Mirror Descent Search (MDS) algorithm which is applicable both for black box optimization problems and reinforcement learning problems. Our method is based on the mirror descent method, which is a general optimization algorithm. The contribution of this research is roughly twofold. We propose two essential algorithms, called MDS and Accelerated Mirror Descent Search (AMDS), and two more approximate algorithms: Gaussian Mirror Descent Search (G-MDS) and Gaussian Accelerated Mirror Descent Search (G-AMDS). This research shows that the advanced methods developed in the context of the mirror descent research can be applied to reinforcement learning problem. We also clarify the relationship between an existing reinforcement learning algorithm and our method. With two evaluation experiments, we show our proposed algorithms converge faster than some state-of-the-art methods.