We revisit the domain of off-policy policy optimization in RL from the perspective of coordinate ascent. One commonly-used approach is to leverage the off-policy policy gradient to optimize a surrogate objective -- the total discounted in expectation return of the target policy with respect to the state distribution of the behavior policy. However, this approach has been shown to suffer from the distribution mismatch issue, and therefore significant efforts are needed for correcting this mismatch either via state distribution correction or a counterfactual method. In this paper, we rethink off-policy learning via Coordinate Ascent Policy Optimization (CAPO), an off-policy actor-critic algorithm that decouples policy improvement from the state distribution of the behavior policy without using the policy gradient. This design obviates the need for distribution correction or importance sampling in the policy improvement step of off-policy policy gradient. We establish the global convergence of CAPO with general coordinate selection and then further quantify the convergence rates of several instances of CAPO with popular coordinate selection rules, including the cyclic and the randomized variants of CAPO. We then extend CAPO to neural policies for a more practical implementation. Through experiments, we demonstrate that CAPO provides a competitive approach to RL in practice.

In classic reinforcement learning algorithms, agents make decisions at discrete and fixed time intervals. The physical duration between one decision and the next becomes a critical hyperparameter. When this duration is too short, the agent needs to make many decisions to achieve its goal, aggravating the problem's difficulty. But when this duration is too long, the agent becomes incapable of controlling the system. Physical systems, however, do not need a constant control frequency. For learning agents, it is desirable to operate with low frequency when possible and high frequency when necessary. We propose a framework called Continuous-Time Continuous-Options (CTCO), where the agent chooses options as sub-policies of variable durations. Such options are time-continuous and can interact with the system at any desired frequency providing a smooth change of actions. The empirical analysis shows that our algorithm is competitive w.r.t. other time-abstraction techniques, such as classic option learning and action repetition, and practically overcomes the difficult choice of the decision frequency.

A central problem in computational biophysics is protein structure prediction, i.e., finding the optimal folding of a given amino acid sequence. This problem has been studied in a classical abstract model, the HP model, where the protein is modeled as a sequence of H (hydrophobic) and P (polar) amino acids on a lattice. The objective is to find conformations maximizing H-H contacts. It is known that even in this reduced setting, the problem is intractable (NP-hard). In this work, we apply deep reinforcement learning (DRL) to the two-dimensional HP model. We can obtain the conformations of best known energies for benchmark HP sequences with lengths from 20 to 50. Our DRL is based on a deep Q-network (DQN). We find that a DQN based on long short-term memory (LSTM) architecture greatly enhances the RL learning ability and significantly improves the search process. DRL can sample the state space efficiently, without the need of manual heuristics. Experimentally we show that it can find multiple distinct best-known solutions per trial. This study demonstrates the effectiveness of deep reinforcement learning in the HP model for protein folding.

As the demand for autonomous driving increases, it is paramount to ensure safety. Early accident prediction using deep learning methods for driving safety has recently gained much attention. In this task, early accident prediction and a point prediction of where the drivers should look are determined, with the dashcam video as input. We propose to exploit the double actors and regularized critics (DARC) method, for the first time, on this accident forecasting platform. We derive inspiration from DARC since it is currently a state-of-the-art reinforcement learning (RL) model on continuous action space suitable for accident anticipation. Results show that by utilizing DARC, we can make predictions 5\% earlier on average while improving in multiple metrics of precision compared to existing methods. The results imply that using our RL-based problem formulation could significantly increase the safety of autonomous driving.

Reinforcement Learning (RL) agents are typically required to operate in dynamic environments, and must develop an ability to quickly adapt to unexpected perturbations in their environment. Promoting this ability is hard, even in single-agent settings Padakandla (2020). For a group this is even more challenging; in addition to the dynamic nature of the environment, agents need to deal with high variance caused by changes in the behavior of other agents. Unsurprisingly, many recent Multi-Agent RL (MARL) works have shown the beneficial effect collaboration between agents has on their performance Xu, Rao, and Bu (2012); Foerster et al. (2016); Lowe et al. (2017); Qian et al. (2019); Jaques et al. (2019); Christianos, Schäfer, and Albrecht (2020). Our objective is to highlight the relationship between a group's ability to collaborate effectively and the group's resilience, which we measure as the group's ability to adapt to perturbations in the environment. Thus, agents that collaborate not only increase their expected utility in a given environment, but are also able to recover a larger fraction of the previous performance after a perturbation occurs. Contrary to investigations of transfer learning Zhu, Lin, and Zhou (2020); Liang and Li (2020) or curriculum learning Portelas et al. (2020), we do not have a stationary target domain in which

We consider a sequential decision making task where we are not allowed to evaluate parameters that violate an a priori unknown (safety) constraint. A common approach is to place a Gaussian process prior on the unknown constraint and allow evaluations only in regions that are safe with high probability. Most current methods rely on a discretization of the domain and cannot be directly extended to the continuous case. Moreover, the way in which they exploit regularity assumptions about the constraint introduces an additional critical hyperparameter. In this paper, we propose an information-theoretic safe exploration criterion that directly exploits the GP posterior to identify the most informative safe parameters to evaluate. Our approach is naturally applicable to continuous domains and does not require additional hyperparameters. We theoretically analyze the method and show that we do not violate the safety constraint with high probability and that we explore by learning about the constraint up to arbitrary precision. Empirical evaluations demonstrate improved data-efficiency and scalability.

Note: This is paper is superseded by the full version (Carroll et al., 2022). Randomly masking and predicting word tokens has been a successful approach in pre-training language models for a variety of downstream tasks. In this work, we observe that the same idea also applies naturally to sequential decision making, where many well-studied tasks like behavior cloning, offline RL, inverse dynamics, and waypoint conditioning correspond to different sequence maskings over a sequence of states, actions, and returns. We introduce the FlexiBiT framework, which provides a unified way to specify models which can be trained on many different sequential decision making tasks. We show that a single FlexiBiT model is simultaneously capable of carrying out many tasks with performance similar to or better than specialized models. Additionally, we show that performance can be further improved by fine-tuning our general model on specific tasks of interest. Masked language modeling (Devlin et al., 2018) is a key technique in natural language processing (NLP). Under this paradigm, models are trained to predict randomly-masked subsets of tokens in a sequence.

We present a new method for generating controllable, dynamically responsive, and photorealistic human animations. Given an image of a person, our system allows the user to generate Physically plausible Upper Body Animation (PUBA) using interaction in the image space, such as dragging their hand to various locations. We formulate a reinforcement learning problem to train a dynamic model that predicts the person's next 2D state (i.e., keypoints on the image) conditioned on a 3D action (i.e., joint torque), and a policy that outputs optimal actions to control the person to achieve desired goals. The dynamic model leverages the expressiveness of 3D simulation and the visual realism of 2D videos. PUBA generates 2D keypoint sequences that achieve task goals while being responsive to forceful perturbation. The sequences of keypoints are then translated by a pose-to-image generator to produce the final photorealistic video.

Michael Chui, Nicolaus Henke, and Mehdi Miremadi, "Most of AI's business uses will be in two areas," McKinsey, March 7, 2019. As companies are recovering from the pandemic, research shows that talent, resilience, tech enablement across all areas, and organic growth are their top priorities. 2 2. What matters most? This article is a collaborative effort by Kimberly Borden, Mark Huntington, Mithun Kamat, Alex Singla, Joris Wijpkema, and Bill Wiseman, representing views from McKinsey's Advanced Industries Practices. Despite this opportunity, many executives remain unsure where to apply AI solutions to capture real bottom-line impact. The result has been slow rates of adoption, with many companies taking a wait-and-see approach rather than diving in.

Ongoing risks from climate change have impacted the livelihood of global nomadic communities, and are likely to lead to increased migratory movements in coming years. As a result, mobility considerations are becoming increasingly important in energy systems planning, particularly to achieve energy access in developing countries. Advanced Plug and Play control strategies have been recently developed with such a decentralized framework in mind, more easily allowing for the interconnection of nomadic communities, both to each other and to the main grid. In light of the above, the design and planning strategy of a mobile multi-energy supply system for a nomadic community is investigated in this work. Motivated by the scale and dimensionality of the associated uncertainties, impacting all major design and decision variables over the 30-year planning horizon, Deep Reinforcement Learning (DRL) is implemented for the design and planning problem tackled. DRL based solutions are benchmarked against several rigid baseline design options to compare expected performance under uncertainty. The results on a case study for ger communities in Mongolia suggest that mobile nomadic energy systems can be both technically and economically feasible, particularly when considering flexibility, although the degree of spatial dispersion among households is an important limiting factor. Key economic, sustainability and resilience indicators such as Cost, Equivalent Emissions and Total Unmet Load are measured, suggesting potential improvements compared to available baselines of up to 25%, 67% and 76%, respectively. Finally, the decomposition of values of flexibility and plug and play operation is presented using a variation of real options theory, with important implications for both nomadic communities and policymakers focused on enabling their energy access.