We were delighted to be joined by Lex Fridman at the San Francisco edition of the Deep Learning Summit, taking part in both a'Deep Dive' session, allowing for a great amount of attendee interaction and collaboration, alongside a fireside chat with OpenAI Co-Founder & Chief Scientist, Ilya Sutskever. The MIT Researcher shared his thoughts on recent developments in AI and its current standing, highlighting its growth in recent years. Lex then referenced, Lee Sedol, the South Korean 9th Dan GO player, whom at this time is the only human to ever beat AI at a video game, which has since become somewhat of an impossible task, describing this feat as a seminal moment and one which changed the course of not only deep learning but also reinforcement learning, increasing the social belief in the subsection of AI. Since then, of course, we have seen video games and tactically based games, including Starcraft become imperative in the development of AI. The comparison of Reinforcement Learning to Human Learning is something which we often come across, referenced by Lex as something which needed addressing, with humans seemingly learning through "very few examples" as opposed to the heavy data sets needed in AI, but why is that?
Our effort is toward unifying GAN and DRL algorithms into a unifying AI model (AGI or general-purpose AI or artificial general intelligence which has general-purpose applications to: (A) offline learning (of stored data) like GAN in (un/semi-/fully-)SL setting such as big data analytics (mining) and visualization; (B) online learning (of real or simulated devices) like DRL in RL setting (with/out environment reward) such as (real or simulated) robotics and control; Our core proposal is adding an (generative/predictive) environment model to the actor-critic (model-free) architecture which results in a model-based actor-critic architecture with temporal-differencing (TD) error and an episodic memory. The proposed AI model is similar to (model-free) DDPG and therefore it's called model-based DDPG. To evaluate it, we compare it with (model-free) DDPG by applying them both to a variety (wide range) of independent simulated robotic and control task environments in OpenAI Gym and Unity Agents. Our initial limited experiments show that DRL and GAN in model-based actor-critic results in an incremental goal-driven intellignce required to solve each task with similar performance to (model-free) DDPG. Our future focus is to investigate the proposed AI model potential to: (A) unify DRL field inside AI by producing competitive performance compared to the best of model-based (PlaNet) and model-free (D4PG) approaches; (B) bridge the gap between AI and robotics communities by solving the important problem of reward engineering with learning the reward function by demonstration;
In many applications, it is desirable to extract only the relevant information from complex input data, which involves making a decision about which input features are relevant. The information bottleneck method formalizes this as an information-theoretic optimization problem by maintaining an optimal tradeoff between compression (throwing away irrelevant input information), and predicting the target. In many problem settings, including the reinforcement learning problems we consider in this work, we might prefer to compress only part of the input. This is typically the case when we have a standard conditioning input, such as a state observation, and a "privileged" input, which might correspond to the goal of a task, the output of a costly planning algorithm, or communication with another agent. In such cases, we might prefer to compress the privileged input, either to achieve better generalization (e.g., with respect to goals) or to minimize access to costly information (e.g., in the case of communication). Practical implementations of the information bottleneck based on variational inference require access to the privileged input in order to compute the bottleneck variable, so although they perform compression, this compression operation itself needs unrestricted, lossless access. In this work, we propose the variational bandwidth bottleneck, which decides for each example on the estimated value of the privileged information before seeing it, i.e., only based on the standard input, and then accordingly chooses stochastically, whether to access the privileged input or not. We formulate a tractable approximation to this framework and demonstrate in a series of reinforcement learning experiments that it can improve generalization and reduce access to computationally costly information.
Standard planners for sequential decision making (including Monte Carlo planning, tree search, dynamic programming, etc.) are constrained by an implicit sequential planning assumption: The order in which a plan is constructed is the same in which it is executed. We consider alternatives to this assumption for the class of goal-directed Reinforcement Learning (RL) problems. Instead of an environment transition model, we assume an imperfect, goal-directed policy. This low-level policy can be improved by a plan, consisting of an appropriate sequence of sub-goals that guide it from the start to the goal state. We propose a planning algorithm, Divide-and-Conquer Monte Carlo Tree Search (DC-MCTS), for approximating the optimal plan by means of proposing intermediate sub-goals which hierarchically partition the initial tasks into simpler ones that are then solved independently and recursively. The algorithm critically makes use of a learned sub-goal proposal for finding appropriate partitions trees of new tasks based on prior experience. Different strategies for learning sub-goal proposals give rise to different planning strategies that strictly generalize sequential planning. We show that this algorithmic flexibility over planning order leads to improved results in navigation tasks in grid-worlds as well as in challenging continuous control environments.
"Value functions are a core component of [RL] systems. The main idea is to to construct a single function approximator V(s; θ) that estimates the long-term reward from any state s, using parameters θ. In this paper we introduce universal value function approximators (UVFAs) V(s, g; θ) that generalise not just over states s but also over goals g." Here is a rigorous, mathematical formulation of RL that treats goals (the high-level objective of the skill to be learned, which should yield good rewards) as a fundamental and necessary input rather than something to be discovered from just the reward signal. The agent is told what it's supposed to do, just as is done in zero-shot learning and actual human learning. It has been 3 years since this was published, and how many papers have cited it since?
The field of meta-learning, or learning-to-learn, has seen a dramatic rise in interest in recent years. Contrary to conventional approaches to AI where a given task is solved from scratch using a fixed learning algorithm, meta-learning aims to improve the learning algorithm itself, given the experience of multiple learning episodes. This paradigm provides an opportunity to tackle many of the conventional challenges of deep learning, including data and computation bottlenecks, as well as the fundamental issue of generalization. In this survey we describe the contemporary meta-learning landscape. We first discuss definitions of meta-learning and position it with respect to related fields, such as transfer learning, multi-task learning, and hyperparameter optimization. We then propose a new taxonomy that provides a more comprehensive breakdown of the space of meta-learning methods today. We survey promising applications and successes of meta-learning including few-shot learning, reinforcement learning and architecture search. Finally, we discuss outstanding challenges and promising areas for future research.
Recently, reinforcement learning (RL) has been used as a tool for finding failures in autonomous systems. During execution, the RL agents often rely on some domain-specific heuristic reward to guide them towards finding failures, but constructing such a heuristic may be difficult or infeasible. Without a heuristic, the agent may only receive rewards at the time of failure, or even rewards that guide it away from failures. For example, some approaches give rewards for taking more-likely actions, because we want to find more-likely failures. However, the agent may then learn to only take likely actions, and may not be able to find a failure at all. Consequently, the problem becomes a hard-exploration problem, where rewards do not aid exploration. A new algorithm, go-explore (GE), has recently set new records on benchmarks from the hard-exploration field. We apply GE to adaptive stress testing (AST), one example of an RL-based falsification approach that provides a way to search for the most-likely failure scenario. We simulate a scenario where an autonomous vehicle drives while a pedestrian is crossing the road. We demonstrate that GE is able to find failures without domain-specific heuristics, such as the distance between the car and the pedestrian, on scenarios that other RL techniques are unable to solve. Furthermore, inspired by the robustification phase of GE, we demonstrate that the backwards algorithm (BA) improves the failures found by other RL techniques.
Potential Based Reward Shaping combined with a potential function based on appropriately defined abstract knowledge has been shown to significantly improve learning speed in Reinforcement Learning. MultiGrid Reinforcement Learning (MRL) has further shown that such abstract knowledge in the form of a potential function can be learned almost solely from agent interaction with the environment. However, we show that MRL faces the problem of not extending well to work with Deep Learning. In this paper we extend and improve MRL to take advantage of modern Deep Learning algorithms such as Deep Q-Networks (DQN). We show that DQN augmented with our approach perform significantly better on continuous control tasks than its Vanilla counterpart and DQN augmented with MRL.
Multi-Agent Reinforcement Learning (MARL) methods find optimal policies for agents that operate in the presence of other learning agents. Central to achieving this is how the agents coordinate. One way to coordinate is by learning to communicate with each other. Can the agents develop a language while learning to perform a common task? In this paper, we formulate and study a MARL problem where cooperative agents are connected to each other via a fixed underlying network. These agents can communicate along the edges of this network by exchanging discrete symbols. However, the semantics of these symbols are not predefined and, during training, the agents are required to develop a language that helps them in accomplishing their goals. We propose a method for training these agents using emergent communication. We demonstrate the applicability of the proposed framework by applying it to the problem of managing traffic controllers, where we achieve state-of-the-art performance as compared to a number of strong baselines. More importantly, we perform a detailed analysis of the emergent communication to show, for instance, that the developed language is grounded and demonstrate its relationship with the underlying network topology. To the best of our knowledge, this is the only work that performs an in depth analysis of emergent communication in a networked MARL setting while being applicable to a broad class of problems.