Although there has been remarkable progress and impressive performance on reinforcement learning (RL) on Atari games, there are many problems with challenging characteristics that have not yet been explored in Deep Learning for RL. These include reward sparsity, abrupt context-dependent reversals of strategy and time-sensitive game play. In this paper, we present Space Fortress, a game that incorporates all these characteristics and experimentally show that the presence of any of these renders state of the art Deep RL algorithms incapable of learning. Then, we present our enhancements to an existing algorithm and show big performance increases through each enhancement through an ablation study. We discuss how each of these enhancements was able to help and also argue that appropriate transfer learning boosts performance.

In the last two articles about Q-learning and Deep Q learning, we worked with value-based reinforcement learning algorithms. To choose which action to take given a state, we take the action with the highest Q-value (maximum expected future reward I will get at each state). As a consequence, in value-based learning, a policy exists only because of these action-value estimates. Today, we'll learn a policy-based reinforcement learning technique called Policy Gradients. The first will learn to keep the bar in balance.

The analysis of complex systems such as inventory control, financial markets, waste-to-energy plants and computer networks is difficult because of the inherent uncertainties in these systems. Risk-aware optimization offers a possible remedy by giving stronger reliability guarantees than the risk-neutral case. Furthermore, it allows expression of the risk attitude of the decision maker. Risk awareness is especially important in sequential decision making because of the dynamic nature of the uncertainty. Markov decision processes (MDPs) introduced by Bellman in [10] provide a mathematical framework for modeling sequential decision making in situations where outcomes are partly random and partly under the control the decision maker. However, in many cases the exact model of the underlying Markov decision process is not known and one can only observe the trajectory of states, actions, and rewards/costs.

We present PRM-RL, a hierarchical method for long-range navigation task completion that combines sampling based path planning with reinforcement learning (RL). The RL agents learn short-range, point-to-point navigation policies that capture robot dynamics and task constraints without knowledge of the large-scale topology. Next, the sampling-based planners provide roadmaps which connect robot configurations that can be successfully navigated by the RL agent. The same RL agents are used to control the robot under the direction of the planning, enabling long-range navigation. We use the Probabilistic Roadmaps (PRMs) for the sampling-based planner. The RL agents are constructed using feature-based and deep neural net policies in continuous state and action spaces. We evaluate PRM-RL, both in simulation and on-robot, on two navigation tasks with non-trivial robot dynamics: end-to-end differential drive indoor navigation in office environments, and aerial cargo delivery in urban environments with load displacement constraints. Our results show improvement in task completion over both RL agents on their own and traditional sampling-based planners. In the indoor navigation task, PRM-RL successfully completes up to 215 m long trajectories under noisy sensor conditions, and the aerial cargo delivery completes flights over 1000 m without violating the task constraints in an environment 63 million times larger than used in training.

Understanding and following directions provided by humans can enable robots to navigate effectively in unknown situations. We present FollowNet, an end-to-end differentiable neural architecture for learning multi-modal navigation policies. FollowNet maps natural language instructions as well as visual and depth inputs to locomotion primitives. FollowNet processes instructions using an attention mechanism conditioned on its visual and depth input to focus on the relevant parts of the command while performing the navigation task. Deep reinforcement learning (RL) a sparse reward learns simultaneously the state representation, the attention function, and control policies. We evaluate our agent on a dataset of complex natural language directions that guide the agent through a rich and realistic dataset of simulated homes. We show that the FollowNet agent learns to execute previously unseen instructions described with a similar vocabulary, and successfully navigates along paths not encountered during training. The agent shows 30% improvement over a baseline model without the attention mechanism, with 52% success rate at novel instructions.

To improve the quality of computation experience for mobile devices, mobile-edge computing (MEC) is a promising paradigm by providing computing capabilities in close proximity within a sliced radio access network (RAN), which supports both traditional communication and MEC services. Nevertheless, the design of computation offloading policies for a virtual MEC system remains challenging. Specifically, whether to execute a computation task at the mobile device or to offload it for MEC server execution should adapt to the time-varying network dynamics. In this paper, we consider MEC for a representative mobile user in an ultra-dense sliced RAN, where multiple base stations (BSs) are available to be selected for computation offloading. The problem of solving an optimal computation offloading policy is modelled as a Markov decision process, where our objective is to maximize the long-term utility performance whereby an offloading decision is made based on the task queue state, the energy queue state as well as the channel qualities between MU and BSs. To break the curse of high dimensionality in state space, we first propose a double deep Q-network (DQN) based strategic computation offloading algorithm to learn the optimal policy without knowing a priori knowledge of network dynamics. Then motivated by the additive structure of the utility function, a Q-function decomposition technique is combined with the double DQN, which leads to novel learning algorithm for the solving of stochastic computation offloading. Numerical experiments show that our proposed learning algorithms achieve a significant improvement in computation offloading performance compared with the baseline policies.

We present a simple model of a non-equilibrium self-organizing market where asset prices are partially driven by investment decisions of a bounded-rational agent. The agent acts in a stochastic market environment driven by various exogenous "alpha" signals, agent's own actions (via market impact), and noise. Unlike traditional agent-based models, our agent aggregates all traders in the market, rather than being a representative agent. Therefore, it can be identified with a bounded-rational component of the market itself, providing a particular implementation of an Invisible Hand market mechanism. In such setting, market dynamics are modeled as a fictitious self-play of such bounded-rational market-agent in its adversarial stochastic environment. As rewards obtained by such self-playing market agent are not observed from market data, we formulate and solve a simple model of such market dynamics based on a neuroscience-inspired Bounded Rational Information Theoretic Inverse Reinforcement Learning (BRIT-IRL). This results in effective asset price dynamics with a non-linear mean reversion - which in our model is generated dynamically, rather than being postulated. We argue that our model can be used in a similar way to the Black-Litterman model. In particular, it represents, in a simple modeling framework, market views of common predictive signals, market impacts and implied optimal dynamic portfolio allocations, and can be used to assess values of private signals. Moreover, it allows one to quantify a "market-implied" optimal investment strategy, along with a measure of market rationality. Our approach is numerically light, and can be implemented using standard off-the-shelf software such as TensorFlow.

Reinforcement learning (RL) is hot! It allows programmers to create software agents that learn to take optimal actions to maximize reward, through trying out different strategies in a given environment. This course will take you through all the core concepts in Reinforcement Learning, transforming a theoretical subject into tangible Python coding exercises with the help of OpenAI Gym. The videos will first guide you through the gym environment, solving the CartPole-v0 toy robotics problem, before moving on to coding up and solving a multi-armed bandit problem in Python. As the course ramps up, it shows you how to use dynamic programming and TensorFlow-based neural networks to solve GridWorld, another OpenAI Gym challenge.

On the forefront of deep learning research is a technique called reinforcement learning, which bridges the gap between academic deep learning problems and ways in which learning occurs in nature in weakly supervised environments. This technique is heavily used when researching areas like learning how to walk, chase prey, navigate complex environments, and even play Go. This session will teach a neural network to play the video game Pong from just the pixels on the screen. No rules, no strategy coaching, and no PhD required. See all the sessions from Google I/O '18 here https://goo.gl/q1Tr8x

In our new paper in Nature Neuroscience, we use the meta-reinforcement learning framework developed in AI research to investigate the role of dopamine in the brain in helping us to learn. Dopamine--commonly known as the brain's pleasure signal--has often been thought of as analogous to the reward prediction error signal used in AI reinforcement learning algorithms. These systems learn to act by trial and error guided by the reward. We propose that dopamine's role goes beyond just using reward to learn the value of past actions and that it plays an integral role, specifically within the prefrontal cortex area, in allowing us to learn efficiently, rapidly and flexibly on new tasks. We tested our theory by virtually recreating six meta-learning experiments from the field of neuroscience--each requiring an agent to perform tasks that use the same underlying principles (or set of skills) but that vary in some dimension.