In this paper, we propose a max-min entropy framework for reinforcement learning (RL) to overcome the limitation of the maximum entropy RL framework in model-free sample-based learning. Whereas the maximum entropy RL framework guides learning for policies to reach states with high entropy in the future, the proposed max-min entropy framework aims to learn to visit states with low entropy and maximize the entropy of these low-entropy states to promote exploration. For general Markov decision processes (MDPs), an efficient algorithm is constructed under the proposed max-min entropy framework based on disentanglement of exploration and exploitation. Numerical results show that the proposed algorithm yields drastic performance improvement over the current state-of-the-art RL algorithms.

The evaluation of rare but high-stakes events remains one of the main difficulties in obtaining reliable policies from intelligent agents, especially in large or continuous state/action spaces where limited scalability enforces the use of a prohibitively large number of testing iterations. On the other hand, a biased or inaccurate policy evaluation in a safety-critical system could potentially cause unexpected catastrophic failures during deployment. In this paper, we propose the Accelerated Policy Evaluation (APE) method, which simultaneously uncovers rare events and estimates the rare event probability in Markov decision processes. The APE method treats the environment nature as an adversarial agent and learns towards, through adaptive importance sampling, the zero-variance sampling distribution for the policy evaluation. Moreover, APE is scalable to large discrete or continuous spaces by incorporating function approximators. We investigate the convergence properties of proposed algorithms under suitable regularity conditions. Our empirical studies show that APE estimates rare event probability with a smaller variance while only using orders of magnitude fewer samples compared to baseline methods in both multi-agent and single-agent environments.

This paper is dedicated to designing provably efficient adversarial imitation learning (AIL) algorithms that directly optimize policies from expert demonstrations. Firstly, we develop a transition-aware AIL algorithm named TAIL with an expert sample complexity of $\tilde{O}(H^{3/2} |S|/\varepsilon)$ under the known transition setting, where $H$ is the planning horizon, $|S|$ is the state space size and $\varepsilon$ is desired policy value gap. This improves upon the previous best bound of $\tilde{O}(H^2 |S| / \varepsilon^2)$ for AIL methods and matches the lower bound of $\tilde{\Omega} (H^{3/2} |S|/\varepsilon)$ in [Rajaraman et al., 2021] up to a logarithmic factor. The key ingredient of TAIL is a fine-grained estimator for expert state-action distribution, which explicitly utilizes the transition function information. Secondly, considering practical settings where the transition functions are usually unknown but environment interaction is allowed, we accordingly develop a model-based transition-aware AIL algorithm named MB-TAIL. In particular, MB-TAIL builds an empirical transition model by interacting with the environment and performs imitation under the recovered empirical model. The interaction complexity of MB-TAIL is $\tilde{O} (H^3 |S|^2 |A| / \varepsilon^2)$, which improves the best known result of $\tilde{O} (H^4 |S|^2 |A| / \varepsilon^2)$ in [Shani et al., 2021]. Finally, our theoretical results are supported by numerical evaluation and detailed analysis on two challenging MDPs.

This 3-course Specialization from Google Cloud and New York Institute of Finance (NYIF) is for finance professionals, including but not limited to hedge fund traders, analysts, day traders, those involved in investment management or portfolio management, and anyone interested in gaining greater knowledge of how to construct effective trading strategies using Machine Learning (ML) and Python. Alternatively, this program can be for Machine Learning professionals who seek to apply their craft to quantitative trading strategies. By the end of the Specialization, you'll understand how to use the capabilities of Google Cloud to develop and deploy serverless, scalable, deep learning, and reinforcement learning models to create trading strategies that can update and train themselves. As a challenge, you're invited to apply the concepts of Reinforcement Learning to use cases in Trading. This program is intended for those who have an understanding of the foundations of Machine Learning at an intermediate level.

This article is part of our reviews of AI research papers, a series of posts that explore the latest findings in artificial intelligence. In a paper published in the peer-reviewed scientific journal Nature last week, scientists at Google Brain introduced a deep reinforcement learning technique for floorplanning, the process of arranging the placement of different components of computer chips. The researchers managed to use the reinforcement learning technique to design the next generation of Tensor Processing Units, Google's specialized artificial intelligence processors. The use of software in chip design is not new. But according to the Google researchers, the new reinforcement learning model "automatically generates chip floorplans that are superior or comparable to those produced by humans in all key metrics, including power consumption, performance and chip area."

In online reinforcement learning (RL), efficient exploration remains particularly challenging in high-dimensional environments with sparse rewards. In low-dimensional environments, where tabular parameterization is possible, count-based upper confidence bound (UCB) exploration methods achieve minimax near-optimal rates. However, it remains unclear how to efficiently implement UCB in realistic RL tasks that involve non-linear function approximation. To address this, we propose a new exploration approach via \textit{maximizing} the deviation of the occupancy of the next policy from the explored regions. We add this term as an adaptive regularizer to the standard RL objective to balance exploration vs. exploitation. We pair the new objective with a provably convergent algorithm, giving rise to a new intrinsic reward that adjusts existing bonuses. The proposed intrinsic reward is easy to implement and combine with other existing RL algorithms to conduct exploration. As a proof of concept, we evaluate the new intrinsic reward on tabular examples across a variety of model-based and model-free algorithms, showing improvements over count-only exploration strategies. When tested on navigation and locomotion tasks from MiniGrid and DeepMind Control Suite benchmarks, our approach significantly improves sample efficiency over state-of-the-art methods. Our code is available at https://github.com/tianjunz/MADE.

Existing observational approaches for learning human preferences, such as inverse reinforcement learning, usually make strong assumptions about the observability of the human's environment. However, in reality, people make many important decisions under uncertainty. To better understand preference learning in these cases, we study the setting of inverse decision theory (IDT), a previously proposed framework where a human is observed making non-sequential binary decisions under uncertainty. In IDT, the human's preferences are conveyed through their loss function, which expresses a tradeoff between different types of mistakes. We give the first statistical analysis of IDT, providing conditions necessary to identify these preferences and characterizing the sample complexity -- the number of decisions that must be observed to learn the tradeoff the human is making to a desired precision. Interestingly, we show that it is actually easier to identify preferences when the decision problem is more uncertain. Furthermore, uncertain decision problems allow us to relax the unrealistic assumption that the human is an optimal decision maker but still identify their exact preferences; we give sample complexities in this suboptimal case as well. Our analysis contradicts the intuition that partial observability should make preference learning more difficult. It also provides a first step towards understanding and improving preference learning methods for uncertain and suboptimal humans.

The capability of reinforcement learning (RL) agent directly depends on the diversity of learning scenarios the environment generates and how closely it captures real-world situations. However, existing environments/simulators lack the support to systematically model distributions over initial states and transition dynamics. Furthermore, in complex domains such as soccer, the space of possible scenarios is infinite, which makes it impossible for one research group to provide a comprehensive set of scenarios to train, test, and benchmark RL algorithms. To address this issue, for the first time, we adopt an existing formal scenario specification language, SCENIC, to intuitively model and generate interactive scenarios. We interfaced SCENIC to Google Research Soccer environment to create a platform called SCENIC4RL. Using this platform, we provide a dataset consisting of 36 scenario programs encoded in SCENIC and demonstration data generated from a subset of them. We share our experimental results to show the effectiveness of our dataset and the platform to train, test, and benchmark RL algorithms. More importantly, we open-source our platform to enable RL community to collectively contribute to constructing a comprehensive set of scenarios.

In this paper, we present an algorithm to efficiently learn socially-compliant navigation policies from observations of human trajectories. As mobile robots come to inhabit and traffic social spaces, they must account for social cues and behave in a socially compliant manner. We focus on learning such cues from examples. We describe an inverse reinforcement learning based algorithm which learns from human trajectory observations without knowing their specific actions. We increase the sample-efficiency of our approach over alternative methods by leveraging the notion of a replay buffer (found in many off-policy reinforcement learning methods) to eliminate the additional sample complexity associated with inverse reinforcement learning. We evaluate our method by training agents using publicly available pedestrian motion data sets and compare it to related methods. We show that our approach yields better performance while also decreasing training time and sample complexity.

One of the main challenges in model-based reinforcement learning (RL) is to decide which aspects of the environment should be modeled. The value-equivalence (VE) principle proposes a simple answer to this question: a model should capture the aspects of the environment that are relevant for value-based planning. Technically, VE distinguishes models based on a set of policies and a set of functions: a model is said to be VE to the environment if the Bellman operators it induces for the policies yield the correct result when applied to the functions. As the number of policies and functions increase, the set of VE models shrinks, eventually collapsing to a single point corresponding to a perfect model. A fundamental question underlying the VE principle is thus how to select the smallest sets of policies and functions that are sufficient for planning. In this paper we take an important step towards answering this question. We start by generalizing the concept of VE to order-$k$ counterparts defined with respect to $k$ applications of the Bellman operator. This leads to a family of VE classes that increase in size as $k \rightarrow \infty$. In the limit, all functions become value functions, and we have a special instantiation of VE which we call proper VE or simply PVE. Unlike VE, the PVE class may contain multiple models even in the limit when all value functions are used. Crucially, all these models are sufficient for planning, meaning that they will yield an optimal policy despite the fact that they may ignore many aspects of the environment. We construct a loss function for learning PVE models and argue that popular algorithms such as MuZero and Muesli can be understood as minimizing an upper bound for this loss. We leverage this connection to propose a modification to MuZero and show that it can lead to improved performance in practice.