The ability to handle single molecules as effectively as macroscopic building-blocks would enable the construction of complex supramolecular structures that are not accessible by self-assembly. The fundamental challenges on the way towards this goal are the uncontrolled variability and poor observability of atomic-scale conformations. Here, we present a strategy to work around both obstacles, and demonstrate autonomous robotic nanofabrication by manipulating single molecules. Our approach employs reinforcement learning (RL), which is able to learn solution strategies even in the face of large uncertainty and with sparse feedback. However, to be useful for autonomous nanofabrication, standard RL algorithms need to be adapted to cope with the limited training opportunities available. We demonstrate the potential of our RL approach by applying it to an exemplary task of subtractive manufacturing, the removal of individual molecules from a molecular layer using a scanning probe microscope (SPM). Our RL agent reaches an excellent performance level, enabling us to automate a task which previously had to be performed by a human. We anticipate that our work opens the way towards autonomous agents for the robotic construction of functional supramolecular structures with speed, precision and perseverance beyond our current capabilities.

Properly used, positive reinforcement is extremely powerful. Tic-Tac-Toe is a simple game. If both sides play perfectly, neither can win. But if one plays imperfectly, the other can exploit the flaws in the other's strategy. Does that sound a little like trading? Reinforcement learning is a machine learning paradigm that can learn behavior to achieve maximum reward in complex dynamic environments, as simple as Tic-Tac-Toe, or as complex as Go, and options trading. In this post, we will try to explain what reinforcement learning is, share code to apply it, and references to learn more about it.

We study minimax methods for off-policy evaluation (OPE) using value-functions and marginalized importance weights. Despite that they hold promises of overcoming the exponential variance in traditional importance sampling, several key problems remain: (1) They require function approximation and are generally biased. For the sake of trustworthy OPE, is there anyway to quantify the biases? (2) They are split into two styles ("weight-learning" vs "value-learning"). Can we unify them? In this paper we answer both questions positively. By slightly altering the derivation of previous methods (one from each style; Uehara et al., 2019), we unify them into a single confidence interval (CI) that automatically comes with a special type of double robustness: when either the value-function or importance weight class is well-specified, the CI is valid and its length quantifies the misspecification of the other class. We can also tell which class is misspecified, which provides useful diagnostic information for the design of function approximation. Our CI also provides a unified view of and new insights to some recent methods: for example, one side of the CI recovers a version of AlgaeDICE (Nachum et al., 2019b), and we show that the two sides need to be used together and either alone may incur doubled approximation error as a point estimate. We further examine the potential of applying these bounds to two long-standing problems: off-policy policy optimization with poor data coverage (i.e., exploitation), and systematic exploration. With a well-specified value-function class, we show that optimizing the lower and the upper bounds lead to effective exploitation and exploration, respectively. Our results also suggests an interesting assymetry between exploration and exploitation, that the former might require substantially weaker realizability assumptions than the latter.

For a robotic grasping task in which diverse unseen target objects exist in a cluttered environment, some deep learning-based methods have achieved state-of-the-art results using visual input directly. In contrast, actor-critic deep reinforcement learning (RL) methods typically perform very poorly when grasping diverse objects, especially when learning from raw images and sparse rewards. To make these RL techniques feasible for vision-based grasping tasks, we employ state representation learning (SRL), where we encode essential information first for subsequent use in RL. However, typical representation learning procedures are unsuitable for extracting pertinent information for learning the grasping skill, because the visual inputs for representation learning, where a robot attempts to grasp a target object in clutter, are extremely complex. We found that preprocessing based on the disentanglement of a raw input image is the key to effectively capturing a compact representation. This enables deep RL to learn robotic grasping skills from highly varied and diverse visual inputs. We demonstrate the effectiveness of this approach with varying levels of disentanglement in a realistic simulated environment.

Imitation Learning (IL) is a popular paradigm for training agents to achieve complicated goals by leveraging expert behavior, rather than dealing with the hardships of designing a correct reward function. With the environment modeled as a Markov Decision Process (MDP), most of the existing IL algorithms are contingent on the availability of expert demonstrations in the same MDP as the one in which a new imitator policy is to be learned. This is uncharacteristic of many real-life scenarios where discrepancies between the expert and the imitator MDPs are common, especially in the transition dynamics function. Furthermore, obtaining expert actions may be costly or infeasible, making the recent trend towards state-only IL (where expert demonstrations constitute only states or observations) ever so promising. Building on recent adversarial imitation approaches that are motivated by the idea of divergence minimization, we present a new state-only IL algorithm in this paper. It divides the overall optimization objective into two subproblems by introducing an indirection step and solves the subproblems iteratively. We show that our algorithm is particularly effective when there is a transition dynamics mismatch between the expert and imitator MDPs, while the baseline IL methods suffer from performance degradation. To analyze this, we construct several interesting MDPs by modifying the configuration parameters for the MuJoCo locomotion tasks from OpenAI Gym 1 .

This paper focuses on inverse reinforcement learning (IRL) to enable safe and efficient autonomous navigation in unknown partially observable environments. The objective is to infer a cost function that explains expert-demonstrated navigation behavior while relying only on the observations and state-control trajectory used by the expert. We develop a cost function representation composed of two parts: a probabilistic occupancy encoder, with recurrent dependence on the observation sequence, and a cost encoder, defined over the occupancy features. The representation parameters are optimized by differentiating the error between demonstrated controls and a control policy computed from the cost encoder. Such differentiation is typically computed by dynamic programming through the value function over the whole state space. We observe that this is inefficient in large partially observable environments because most states are unexplored. Instead, we rely on a closed-form subgradient of the cost-to-go obtained only over a subset of promising states via an efficient motion-planning algorithm such as A* or RRT. Our experiments show that our model exceeds the accuracy of baseline IRL algorithms in robot navigation tasks, while substantially improving the efficiency of training and test-time inference.

Optimistic initialisation is an effective strategy for efficient exploration in reinforcement learning (RL). In the tabular case, all provably efficient model-free algorithms rely on it. However, model-free deep RL algorithms do not use optimistic initialisation despite taking inspiration from these provably efficient tabular algorithms. In particular, in scenarios with only positive rewards, Q-values are initialised at their lowest possible values due to commonly used network initialisation schemes, a pessimistic initialisation. Merely initialising the network to output optimistic Q-values is not enough, since we cannot ensure that they remain optimistic for novel state-action pairs, which is crucial for exploration. We propose a simple count-based augmentation to pessimistically initialised Q-values that separates the source of optimism from the neural network. We show that this scheme is provably efficient in the tabular setting and extend it to the deep RL setting. Our algorithm, Optimistic Pessimistically Initialised Q-Learning (OPIQ), augments the Q-value estimates of a DQN-based agent with count-derived bonuses to ensure optimism during both action selection and bootstrapping. We show that OPIQ outperforms non-optimistic DQN variants that utilise a pseudocount-based intrinsic motivation in hard exploration tasks, and that it predicts optimistic estimates for novel state-action pairs.

Reinforcement learning (RL) has emerged as a standard approach for building an intelligent system, which involves multiple self-operated agents to collectively accomplish a designated task. More importantly, there has been a great attention to RL since the introduction of deep learning that essentially makes RL feasible to operate in high-dimensional environments. However, current research interests are diverted into different directions, such as multi-agent and multi-objective learning, and human-machine interactions. Therefore, in this paper, we propose a comprehensive software architecture that not only plays a vital role in designing a connect-the-dots deep RL architecture but also provides a guideline to develop a realistic RL application in a short time span. By inheriting the proposed architecture, software managers can foresee any challenges when designing a deep RL-based system. As a result, they can expedite the design process and actively control every stage of software development, which is especially critical in agile development environments. For this reason, we designed a deep RL-based framework that strictly ensures flexibility, robustness, and scalability. Finally, to enforce generalization, the proposed architecture does not depend on a specific RL algorithm, a network configuration, the number of agents, or the type of agents.

Multi-agent learning distinctly poses significant challenges in the effort to allocate a concealed communication medium. Agents receive thorough knowledge from the medium to determine subsequent actions in a distributed nature. Apparently, the goal is to leverage the cooperation of multiple agents to achieve a designated objective efficiently. Recent studies typically combine a specialized neural network with reinforcement learning to enable communication between agents. This approach, however, limits the number of agents or necessitates the homogeneity of the system. In this paper, we have proposed a more scalable approach that not only deals with a great number of agents but also enables collaboration between dissimilar functional agents and compatibly combined with any deep reinforcement learning methods. Specifically, we create a global communication map to represent the status of each agent in the system visually. The visual map and the environmental state are fed to a shared-parameter network to train multiple agents concurrently. Finally, we select the Asynchronous Advantage Actor-Critic (A3C) algorithm to demonstrate our proposed scheme, namely Visual communication map for Multi-agent A3C (VMA3C). Simulation results show that the use of visual communication map improves the performance of A3C regarding learning speed, reward achievement, and robustness in multi-agent problems.

The intelligent control of traffic signal is critical to the optimization of transportation systems. To solve the problem in large-scale road networks, recent research has focused on interactions among intersections, which have shown promising results. However, existing studies pay more attention to the sensation sharing among agents and do not care about the results after taking each action. In this paper, we propose a novel multi-agent interaction mechanism, defined as Gamma-Reward that includes both original Gamma-Reward and Gamma-Attention-Reward, which use the space-time information in the replay buffer to amend the reward of each action, for traffic signal control based on deep reinforcement learning method. We give a detailed theoretical foundation and prove the proposed method can converge to Nash Equilibrium. By extending the idea of Markov Chain to the road network, this interaction mechanism replaces the graph attention method and realizes the decoupling of the road network, which is more in line with practical applications. Simulation and experiment results demonstrate that the proposed model can get better performance than previous studies, by amending the reward. To our best knowledge, our work appears to be the first to treat the road network itself as a Markov Chain.