It is difficult not to smile when reading the Wall Street Journal report about a guest in a robot-staffed hotel in Japan who was woken every few hours by the in-room assistant asking him to repeat his command. The hotel manager finally realized that heavy snoring by the guest had triggered the robot's voice recognition system. For every clanger, though, there is also a success story. For example, DeepMind's AI programme AlphaStar has for the first time beaten human video game players at StarCraft II, winning 10 games in a row. AlphaStar's success demonstrated the ability of AI programmes, in this case based on a reinforcement learning algorithm, to make quick decisions without any errors while operating in a complex environment.

Developments in artificial intelligence often draw inspiration from how humans think, but now AI has turned the tables to teach us about how brains learn. Will Dabney at tech firm DeepMind in London and his colleagues have found that a recent development in machine learning called distributional reinforcement learning also provides a new explanation for how the reward pathways in the brain work. These pathways govern our response to pleasurable events and are mediated by neurons that release the brain chemical dopamine. "Dopamine in the brain is a type of surprise signal," says Dabney. "When things turn out better than expected, more dopamine gets released."

In this paper, a novel racing environment for OpenAI Gym is introduced. This environment operates with continuous action- and state-spaces and requires agents to learn to control the acceleration and steering of a car while navigating a randomly generated racetrack. Different versions of two actor-critic learning algorithms are tested on this environment: Sampled Policy Gradient (SPG) and Proximal Policy Optimization (PPO). An extension of SPG is introduced that aims to improve learning performance by weighting action samples during the policy update step. The effect of using experience replay (ER) is also investigated. To this end, a modification to PPO is introduced that allows for training using old action samples by optimizing the actor in log space. Finally, a new technique for performing ER is tested that aims to improve learning speed without sacrificing performance by splitting the training into two parts, whereby networks are first trained using state transitions from the replay buffer, and then using only recent experiences. The results indicate that experience replay is not beneficial to PPO in continuous action spaces. The training of SPG seems to be more stable when actions are weighted. All versions of SPG outperform PPO when ER is used. The ER trick is effective at improving training speed on a computationally less intensive version of SPG.

We show that reinforcement learning agents that learn by surprise (surprisal) get stuck at abrupt environmental transition boundaries because these transitions are difficult to learn. We propose a counter-intuitive solution that we call Mutual Information Minimising Exploration (MIME) where an agent learns a latent representation of the environment without trying to predict the future states. We show that our agent performs significantly better over sharp transition boundaries while matching the performance of surprisal driven agents elsewhere. In particular, we show state-of-the-art performance on difficult learning games such as Gravitar, Montezuma's Revenge and Doom.

Intelligent Object manipulation for grasping is a challenging problem for robots. Unlike robots, humans almost immediately know how to manipulate objects for grasping due to learning over the years. A grown woman can grasp objects more skilfully than a child because of learning skills developed over years, the absence of which in the present day robotic grasping compels it to perform well below the human object grasping benchmarks. In this paper we have taken up the challenge of developing learning based pose estimation by decomposing the problem into both position and orientation learning. More specifically, for grasp position estimation, we explore three different methods - a Genetic Algorithm (GA) based optimization method to minimize error between calculated image points and predicted end-effector (EE) position, a regression based method (RM) where collected data points of robot EE and image points have been regressed with a linear model, a PseudoInverse (PI) model which has been formulated in the form of a mapping matrix with robot EE position and image points for several observations. Further for grasp orientation learning, we develop a deep reinforcement learning (DRL) model which we name as Grasp Deep Q-Network (GDQN) and benchmarked our results with Modified VGG16 (MVGG16). Rigorous experimentations show that due to inherent capability of producing very high-quality solutions for optimization problems and search problems, GA based predictor performs much better than the other two models for position estimation. For orientation learning results indicate that off policy learning through GDQN outperforms MVGG16, since GDQN architecture is specially made suitable for the reinforcement learning. Based on our proposed architectures and algorithms, the robot is capable of grasping all rigid body objects having regular shapes.

Ensemble learning is a very prevalent method employed in machine learning. The relative success of ensemble methods is attributed to its ability to tackle a wide range of instances and complex problems that require different low-level approaches. However, ensemble methods are relatively less popular in reinforcement learning owing to the high sample complexity and computational expense involved. We present a new training and evaluation framework for model-free algorithms that use ensembles of policies obtained from a single training instance. These policies are diverse in nature and are learned through directed perturbation of the model parameters at regular intervals. We show that learning an adequately diverse set of policies is required for a good ensemble while extreme diversity can prove detrimental to overall performance. We evaluate our approach to challenging discrete and continuous control tasks and also discuss various ensembling strategies. Our framework is substantially sample efficient, computationally inexpensive and is seen to outperform state of the art(SOTA) scores in Atari 2600 and Mujoco. Video results can be found at https://www.youtube.com/channel/UC95Kctu9Mp8BlFmtGD2TGTA

We present a new model-based reinforcement learning algorithm, Cooperative Prioritized Sweeping, for efficient learning in multi-agent Markov decision processes. The algorithm allows for sample-efficient learning on large problems by exploiting a factorization to approximate the value function. Our approach only requires knowledge about the structure of the problem in the form of a dynamic decision network. Using this information, our method learns a model of the environment and performs temporal difference updates which affect multiple joint states and actions at once. Batch updates are additionally performed which efficiently back-propagate knowledge throughout the factored Q-function. Our method outperforms the state-of-the-art algorithm sparse cooperative Q-learning algorithm, both on the well-known SysAdmin benchmark and randomized environments.

Social dilemma situations bring out the conflict between individual and group rationality. When individuals act rationally in such situations, the group suffers sub-optimal outcomes. The Iterative Prisoner's Dilemma (IPD) is a two-player game that offers a theoretical framework to model and study such social situations. In the Prisoner's Dilemma, individualistic behavior leads to mutual defection and sub-optimal outcomes. This result is in contrast to what one observes in human groups, where humans often sacrifice individualistic behavior for the good of the collective. It is interesting to study how and why such cooperative and individually irrational behavior emerges in human groups. To this end, recent work models this problem by treating each player as a Deep Reinforcement Learning (RL) agent and evolves cooperative behavioral policies through internal information or reward sharing mechanisms. We propose an approach to evolve cooperative behavior between RL agents playing the IPD game without sharing rewards, internal details (weights, gradients), or a communication channel. We introduce a Status-Quo loss (SQLoss) that incentivizes cooperative behavior by encouraging policy stationarity. We also describe an approach to transform a two-player game (with visual inputs) into its IPD formulation through self-supervised skill discovery (IPDistill).We show how our approach outperforms existing approaches in the Iterative Prisoner's Dilemma and the two-player Coin game.

In recent years, the emergence of deep reinforcement learning (RL) has resulted in the growing demand for their evaluation. To implement and test RL models quickly and reliably, several RL libraries have been developed. Pyqlearning is a Python library to implement RL, especially for Q-Learning and multi-agent Deep Q-Network. This library makes it possible to design the information search algorithm such as the Game AI, web crawlers, or robotics. Keras-RL seamlessly implements state-of-the-art deep reinforcement learning algorithms with the deep learning library Keras.

Apply machine, deep and reinforcement learning to finance to crack the markets.