Temporal-Difference (TD) learning is a general and very useful tool for estimating the value function of a given policy, which in turn is required to find good policies. Generally speaking, TD learning updates states whenever they are visited. When the agent lands in a state, its value can be used to compute the TD-error, which is then propagated to other states. However, it may be interesting, when computing updates, to take into account other information than whether a state is visited or not. For example, some states might be more important than others (such as states which are frequently seen in a successful trajectory). Or, some states might have unreliable value estimates (for example, due to partial observability or lack of data), making their values less desirable as targets. We propose an approach to re-weighting states used in TD updates, both when they are the input and when they provide the target for the update. We prove that our approach converges with linear function approximation and illustrate its desirable empirical behaviour compared to other TD-style methods.

The difficulty in specifying rewards for many real-world problems has led to an increased focus on learning rewards from human feedback, such as demonstrations. However, there are often many different reward functions that explain the human feedback, leaving agents with uncertainty over what the true reward function is. While most policy optimization approaches handle this uncertainty by optimizing for expected performance, many applications demand risk-averse behavior. We derive a novel policy gradient-style robust optimization approach, PG-BROIL, that optimizes a soft-robust objective that balances expected performance and risk. To the best of our knowledge, PG-BROIL is the first policy optimization algorithm robust to a distribution of reward hypotheses which can scale to continuous MDPs. Results suggest that PG-BROIL can produce a family of behaviors ranging from risk-neutral to risk-averse and outperforms state-of-the-art imitation learning algorithms when learning from ambiguous demonstrations by hedging against uncertainty, rather than seeking to uniquely identify the demonstrator's reward function.

Google has developed an artificial intelligence that it says is capable of creating computer chips in'under six hours,' according to a new study. The research, published in Nature, notes that humans can take'months' to design specialized chips for its tensor processing units - a type of chip used in AI - but the reinforcement learning (RL) algorithm is better and faster than humans at creating more complex AI. 'The RL agent becomes better and faster at floorplanning optimization as it places a greater number of chip netlists,' the researchers wrote in the study. 'We show that our method can generate chip floorplans that are comparable or superior to human experts in under six hours, whereas humans take months to produce acceptable floorplans for modern accelerators.' Google developed an artificial intelligence that it says is capable of creating computer chips in'under six hours' The new process was used in Google's latest TPU chip, Anna Goldie, one of the study's co-authors said The chip floorplan is where parts such as CPUs, GPUs and memory have been placed on the silicon.

In their decades-long chase to create artificial intelligence, computer scientists have designed and developed all kinds of complicated mechanisms and technologies to replicate vision, language, reasoning, motor skills, and other abilities associated with intelligent life. While these efforts have resulted in AI systems that can efficiently solve specific problems in limited environments, they fall short of developing the kind of general intelligence seen in humans and animals. In a new paper submitted to the peer-reviewed Artificial Intelligence journal, scientists at U.K.-based AI lab DeepMind argue that intelligence and its associated abilities will emerge not from formulating and solving complicated problems but by sticking to a simple but powerful principle: reward maximization. Titled "Reward is Enough," the paper, which is still in pre-proof as of this writing, draws inspiration from studying the evolution of natural intelligence as well as drawing lessons from recent achievements in artificial intelligence. The authors suggest that reward maximization and trial-and-error experience are enough to develop behavior that exhibits the kind of abilities associated with intelligence.

Games are abstractions of the real world, where artificial agents learn to compete and cooperate with other agents. While significant achievements have been made in various perfect- and imperfect-information games, DouDizhu (a.k.a. Fighting the Landlord), a three-player card game, is still unsolved. DouDizhu is a very challenging domain with competition, collaboration, imperfect information, large state space, and particularly a massive set of possible actions where the legal actions vary significantly from turn to turn. Unfortunately, modern reinforcement learning algorithms mainly focus on simple and small action spaces, and not surprisingly, are shown not to make satisfactory progress in DouDizhu. In this work, we propose a conceptually simple yet effective DouDizhu AI system, namely DouZero, which enhances traditional Monte-Carlo methods with deep neural networks, action encoding, and parallel actors. Starting from scratch in a single server with four GPUs, DouZero outperformed all the existing DouDizhu AI programs in days of training and was ranked the first in the Botzone leaderboard among 344 AI agents. Through building DouZero, we show that classic Monte-Carlo methods can be made to deliver strong results in a hard domain with a complex action space. The code and an online demo are released at https://github.com/kwai/DouZero with the hope that this insight could motivate future work.

Deep learning has become an increasingly popular and powerful option for modern pattern recognition systems. However, many deep neural networks have millions to billions of parameters, making them untenable for real-world applications with constraints on memory or latency. As a result, powerful network compression techniques are a must for the widespread adoption of deep learning. We present DECORE, a reinforcement learning approach to automate the network compression process. Using a simple policy gradient method to learn which neurons or channels to keep or remove, we are able to achieve compression rates 3x to 5x greater than contemporary approaches. In contrast with other architecture search methods, DECORE is simple and quick to train, requiring only a few hours of training on 1 GPU. When applied to standard network architectures on different datasets, our approach achieves 11x to 103x compression on different architectures while maintaining accuracies similar to those of the original, large networks.

We propose a practical approach to computing market prices and allocations via a deep reinforcement learning policymaker agent, operating in an environment of other learning agents. Compared to the idealized market equilibrium outcome -- which we use as a benchmark -- our policymaker is much more flexible, allowing us to tune the prices with regard to diverse objectives such as sustainability and resource wastefulness, fairness, buyers' and sellers' welfare, etc. To evaluate our approach, we design a realistic market with multiple and diverse buyers and sellers. Additionally, the sellers, which are deep learning agents themselves, compete for resources in a common-pool appropriation environment based on bio-economic models of commercial fisheries. We demonstrate that: (a) The introduced policymaker is able to achieve comparable performance to the market equilibrium, showcasing the potential of such approaches in markets where the equilibrium prices can not be efficiently computed. (b) Our policymaker can notably outperform the equilibrium solution on certain metrics, while at the same time maintaining comparable performance for the remaining ones. (c) As a highlight of our findings, our policymaker is significantly more successful in maintaining resource sustainability, compared to the market outcome, in scarce resource environments.

Artificial intelligence (AI) has been transforming the practice of drug discovery in the past decade. Various AI techniques have been used in a wide range of applications, such as virtual screening and drug design. In this perspective, we first give an overview on drug discovery and discuss related applications, which can be reduced to two major tasks, i.e., molecular property prediction and molecule generation. We then discuss common data resources, molecule representations and benchmark platforms. Furthermore, to summarize the progress in AI-driven drug discovery, we present the relevant AI techniques including model architectures and learning paradigms in the surveyed papers. We expect that the perspective will serve as a guide for researchers who are interested in working at this intersected area of artificial intelligence and drug discovery. We also provide a GitHub repository\footnote{\url{https://github.com/dengjianyuan/Survey_AI_Drug_Discovery}} with the collection of papers and codes, if applicable, as a learning resource, which will be regularly updated.

The advances in artificial intelligence enabled by deep learning architectures are undeniable. In several cases, deep neural network driven models have surpassed human level performance in benchmark autonomy tasks. The underlying policies for these agents, however, are not easily interpretable. In fact, given their underlying deep models, it is impossible to directly understand the mapping from observations to actions for any reasonably complex agent. Producing this supporting technology to "open the black box" of these AI systems, while not sacrificing performance, was the fundamental goal of the DARPA XAI program. In our journey through this program, we have several "big picture" takeaways: 1) Explanations need to be highly tailored to their scenario; 2) many seemingly high performing RL agents are extremely brittle and are not amendable to explanation; 3) causal models allow for rich explanations, but how to present them isn't always straightforward; and 4) human subjects conjure fantastically wrong mental models for AIs, and these models are often hard to break. This paper discusses the origins of these takeaways, provides amplifying information, and suggestions for future work.

Measuring and promoting policy diversity is critical for solving games with strong non-transitive dynamics where strategic cycles exist, and there is no consistent winner (e.g., Rock-Paper-Scissors). With that in mind, maintaining a pool of diverse policies via open-ended learning is an attractive solution, which can generate auto-curricula to avoid being exploited. However, in conventional open-ended learning algorithms, there are no widely accepted definitions for diversity, making it hard to construct and evaluate the diverse policies. In this work, we summarize previous concepts of diversity and work towards offering a unified measure of diversity in multi-agent open-ended learning to include all elements in Markov games, based on both Behavioral Diversity (BD) and Response Diversity (RD). At the trajectory distribution level, we re-define BD in the state-action space as the discrepancies of occupancy measures. For the reward dynamics, we propose RD to characterize diversity through the responses of policies when encountering different opponents. We also show that many current diversity measures fall in one of the categories of BD or RD but not both. With this unified diversity measure, we design the corresponding diversity-promoting objective and population effectivity when seeking the best responses in open-ended learning. We validate our methods in both relatively simple games like matrix game, non-transitive mixture model, and the complex \textit{Google Research Football} environment. The population found by our methods reveals the lowest exploitability, highest population effectivity in matrix game and non-transitive mixture model, as well as the largest goal difference when interacting with opponents of various levels in \textit{Google Research Football}.