We employ Proximal Iteration for value-function optimization in reinforcement learning. Proximal Iteration is a computationally efficient technique that enables us to bias the optimization procedure towards more desirable solutions. As a concrete application of Proximal Iteration in deep reinforcement learning, we endow the objective function of the Deep Q-Network (DQN) agent with a proximal term to ensure that the online-network component of DQN remains in the vicinity of the target network. The resultant agent, which we call DQN with Proximal Iteration, or DQNPro, exhibits significant improvements over the original DQN on the Atari benchmark. Our results accentuate the power of employing sound optimization techniques for deep reinforcement learning.

Quantum computing has promised significant improvement in solving difficult computational tasks over classical computers. Designing quantum circuits for practical use, however, is not a trivial objective and requires expert-level knowledge. To aid this endeavor, this paper proposes a machine learning-based method to construct quantum circuit architectures. Previous works have demonstrated that classical deep reinforcement learning (DRL) algorithms can successfully construct quantum circuit architectures without encoded physics knowledge. However, these DRL-based works are not generalizable to settings with changing device noises, thus requiring considerable amounts of training resources to keep the RL models up-to-date. With this in mind, we incorporated continual learning to enhance the performance of our algorithm. In this paper, we present the Probabilistic Policy Reuse with deep Q-learning (PPR-DQL) framework to tackle this circuit design challenge. By conducting numerical simulations over various noise patterns, we demonstrate that the RL agent with PPR was able to find the quantum gate sequence to generate the two-qubit Bell state faster than the agent that was trained from scratch. The proposed framework is general and can be applied to other quantum gate synthesis or control problems -- including the automatic calibration of quantum devices.

Reinforcement learning (RL) has gained increasing attraction in the academia and tech industry with launches to a variety of impactful applications and products. Although research is being actively conducted on many fronts (e.g., offline RL, performance, etc.), many RL practitioners face a challenge that has been largely ignored: determine whether a designed Markov Decision Process (MDP) is valid and meaningful. This study proposes a heuristic-based feature analysis method to validate whether an MDP is well formulated. We believe an MDP suitable for applying RL should contain a set of state features that are both sensitive to actions and predictive in rewards. We tested our method in constructed environments showing that our approach can identify certain invalid environment formulations. As far as we know, performing validity analysis for RL problem formulation is a novel direction. We envision that our tool will serve as a motivational example to help practitioners apply RL in real-world problems more easily.

Reinforcement Learning (RL) enables agents to learn how to perform various tasks from scratch. In domains like autonomous driving, recommendation systems, and more, optimal RL policies learned could cause a privacy breach if the policies memorize any part of the private reward. We study the set of existing differentially-private RL policies derived from various RL algorithms such as Value Iteration, Deep Q Networks, and Vanilla Proximal Policy Optimization. We propose a new Privacy-Aware Inverse RL (PRIL) analysis framework, that performs reward reconstruction as an adversarial attack on private policies that the agents may deploy. For this, we introduce the reward reconstruction attack, wherein we seek to reconstruct the original reward from a privacy-preserving policy using an Inverse RL algorithm. An adversary must do poorly at reconstructing the original reward function if the agent uses a tightly private policy. Using this framework, we empirically test the effectiveness of the privacy guarantee offered by the private algorithms on multiple instances of the FrozenLake domain of varying complexities. Based on the analysis performed, we infer a gap between the current standard of privacy offered and the standard of privacy needed to protect reward functions in RL. We do so by quantifying the extent to which each private policy protects the reward function by measuring distances between the original and reconstructed rewards.

With the emerging technologies in Intelligent Transportation System (ITS), the adaptive operation of road space is likely to be realised within decades. An intelligent street can learn and improve its decision-making on the right-of-way (ROW) for road users, liberating more active pedestrian space while maintaining traffic safety and efficiency. However, there is a lack of effective controlling techniques for these adaptive street infrastructures. To fill this gap in existing studies, we formulate this control problem as a Markov Game and develop a solution based on the multi-agent Deep Deterministic Policy Gradient (MADDPG) algorithm. The proposed model can dynamically assign ROW for sidewalks, autonomous vehicles (AVs) driving lanes and on-street parking areas in real-time. Integrated with the SUMO traffic simulator, this model was evaluated using the road network of the South Kensington District against three cases of divergent traffic conditions: pedestrian flow rates, AVs traffic flow rates and parking demands. Results reveal that our model can achieve an average reduction of 3.87% and 6.26% in street space assigned for on-street parking and vehicular operations. Combined with space gained by limiting the number of driving lanes, the average proportion of sidewalks to total widths of streets can significantly increase by 10.13%.

The Arcade Learning Environment (ALE) is proposed as an evaluation platform for empirically assessing the generality of agents across dozens of Atari 2600 games. ALE offers various challenging problems and has drawn significant attention from the deep reinforcement learning (RL) community. From Deep Q-Networks (DQN) to Agent57, RL agents seem to achieve superhuman performance in ALE. However, is this the case? In this paper, to explore this problem, we first review the current evaluation metrics in the Atari benchmarks and then reveal that the current evaluation criteria of achieving superhuman performance are inappropriate, which underestimated the human performance relative to what is possible. To handle those problems and promote the development of RL research, we propose a novel Atari benchmark based on human world records (HWR), which puts forward higher requirements for RL agents on both final performance and learning efficiency. Furthermore, we summarize the state-of-the-art (SOTA) methods in Atari benchmarks and provide benchmark results over new evaluation metrics based on human world records. We concluded that at least four open challenges hinder RL agents from achieving superhuman performance from those new benchmark results. Finally, we also discuss some promising ways to handle those problems.

Meta-reinforcement learning (meta-RL) algorithms enable agents to adapt quickly to tasks from few samples in dynamic environments. Such a feat is achieved through dynamic representations in an agent's policy network (obtained via reasoning about task context, model parameter updates, or both). However, obtaining rich dynamic representations for fast adaptation beyond simple benchmark problems is challenging due to the burden placed on the policy network to accommodate different policies. This paper addresses the challenge by introducing neuromodulation as a modular component to augment a standard policy network that regulates neuronal activities in order to produce efficient dynamic representations for task adaptation. The proposed extension to the policy network is evaluated across multiple discrete and continuous control environments of increasing complexity. To prove the generality and benefits of the extension in meta-RL, the neuromodulated network was applied to two state-of-the-art meta-RL algorithms (CAVIA and PEARL). The result demonstrates that meta-RL augmented with neuromodulation produces significantly better result and richer dynamic representations in comparison to the baselines.

Sepsis is a potentially life-threatening condition, occurs when your body has an unusually severe response to an infection. Some sepsis treatments lead to a patient's deterioration. Hence, selecting the optimal therapy is a challenging task. In recent years, Machine learning has successfully framed many sequential decision-making problems. Scientists at MIT and elsewhere do the same.

I have been studying reinforcement learning since November 2018 when I learned what is was during my time with Insight Data Science. I was an artificial intelligence fellow and I was so fascinated by this idea that you could simulate an environment and get an agent to learn an optimal policy to maximize rewards from that environment. The more I read about RL the more I noticed men were using RL to either train robots or using it to create and play video games. I thought this was such a whack idea! Robots are really cool but reinforcement learning could be used for so much more, I just didn't have any examples of how it could be done yet so I imagined one possibility for using reinforcement learning in an educational environment.

Since AlphaGo, AI researchers have recognized the promise of integrating reinforcement learning with search methods, which involve considering many potential next actions available to an RL agent, and simulating what their results might be before choosing one. This starts to mimic human deliberation much more closely, by explicitly introducing elements of "planning" into the RL paradigm. Yang attributes the huge performance improvements of AlphaGo, AlphaZero and MuZero to this search process. Another important distinction in RL is between model-based systems, which construct explicit models of their environments, and model-free systems, which don't. Prior to AlphaGo, just about all leading RL work was done on model-free systems (PPO and deep Q learning, for example). Model-based systems just weren't practical because the learning environment models is hard, and adds a significant layer of complexity on top of the simpler action selection task that model-free systems could focus on exclusively.