When observed decisions depend only on observed features, off-policy policy evaluation (OPE) methods for sequential decision making problems can estimate the performance of evaluation policies before deploying them. This assumption is frequently violated due to unobserved confounders, unrecorded variables that impact both the decisions and their outcomes. We assess robustness of OPE methods under unobserved confounding by developing worst-case bounds on the performance of an evaluation policy. When unobserved confounders can affect every decision in an episode, we demonstrate that even small amounts of per-decision confounding can heavily bias OPE methods. Fortunately, in a number of important settings found in healthcare, policy-making, operations, and technology, unobserved confounders may primarily affect only one of the many decisions made. Under this less pessimistic model of one-decision confounding, we propose an efficient loss-minimization-based procedure for computing worst-case bounds, and prove its statistical consistency. On two simulated healthcare examples---management of sepsis patients and developmental interventions for autistic children---where this is a reasonable model of confounding, we demonstrate that our method invalidates non-robust results and provides meaningful certificates of robustness, allowing reliable selection of policies even under unobserved confounding.

Recent advances in deep reinforcement learning require a large amount of training data and generally result in representations that are often over specialized to the target task. In this work, we present a methodology to study the underlying potential causes for this specialization. We use the recently proposed projection weighted Canonical Correlation Analysis (PWCCA) to measure the similarity of visual representations learned in the same environment by performing different tasks. We then leverage our proposed methodology to examine the task dependence of visual representations learned on related but distinct embodied navigation tasks. Surprisingly, we find that slight differences in task have no measurable effect on the visual representation for both SqueezeNet and ResNet architectures. We then empirically demonstrate that visual representations learned on one task can be effectively transferred to a different task.

The landmark achievements of AlphaGo Zero have created great research interest into self-play in reinforcement learning. In self-play, Monte Carlo Tree Search is used to train a deep neural network, that is then used in tree searches. Training itself is governed by many hyperparameters.There has been surprisingly little research on design choices for hyper-parameter values and loss-functions, presumably because of the prohibitive computational cost to explore the parameter space. In this paper, we investigate 12 hyper-parameters in an AlphaZero-like self-play algorithm and evaluate how these parameters contribute to training. We use small games, to achieve meaningful exploration with moderate computational effort. The experimental results show that training is highly sensitive to hyper-parameter choices. Through multi-objective analysis we identify 4 important hyper-parameters to further assess. To start, we find surprising results where too much training can sometimes lead to lower performance. Our main result is that the number of self-play iterations subsumes MCTS-search simulations, game-episodes, and training epochs. The intuition is that these three increase together as self-play iterations increase, and that increasing them individually is sub-optimal. A consequence of our experiments is a direct recommendation for setting hyper-parameter values in self-play: the overarching outer-loop of self-play iterations should be maximized, in favor of the three inner-loop hyper-parameters, which should be set at lower values. A secondary result of our experiments concerns the choice of optimization goals, for which we also provide recommendations.

Amazon SageMaker is a fully managed service that enables developers and data scientists to quickly and easily build, train, and deploy machine learning (ML) models at any scale. In addition to building ML models using more commonly used supervised and unsupervised learning techniques, you can also build reinforcement learning (RL) models using Amazon SageMaker RL. Amazon SageMaker RL includes pre-built RL libraries and algorithms that make it easy to get started with reinforcement learning. For more information, see Amazon SageMaker RL – Managed Reinforcement Learning with Amazon Sagemaker. Amazon SageMaker RL makes it easy to integrate with various simulation environments such as AWS RoboMaker, Open AI Gym, open-source environments, and custom-built environments for training RL models.

Grid Date added (newest) Uploads Reinforcement Learning (Machine Learning TMLS20_T0139 Spring 2020) - Duration: 1 hour, 11 minutes. School of AI January 2020 One shot object detection & YOLOv3 by Ivan Goncharov - Duration: 43 minutes. Knowledge is the power Earthling Ed's talk in the Netherlands - Duration: 43 minutes. Our road trip Zwillbrocker Venn Flamingo watch - Duration: 2 minutes, 14 seconds. Reinforcement Learning a SLAM Based Approach - Duration: 3 minutes, 3 seconds.

In the optimization of dynamic systems, the variables typically have constraints. Such problems can be modeled as a constrained Markov Decision Process (MDP). This paper considers a model-free approach to the problem, where the transition probabilities are not known. In the presence of peak constraints, the agent has to choose the policy to maximize the long-term average reward as well as satisfy the constraints at each time. We propose modifications to the standard Q-learning problem for unconstrained optimization to come up with an algorithm with peak constraints. The proposed algorithm is shown to achieve $O(T^{1/2+\gamma})$ regret bound for the obtained reward, and $O(T^{1-\gamma})$ regret bound for the constraint violation for any $\gamma \in(0,1/2)$ and time-horizon $T$. We note that these are the first results on regret analysis for constrained MDP, where the transition problems are not known apriori. We demonstrate the proposed algorithm on an energy harvesting problem where it outperforms state-of-the-art and performs close to the theoretical upper bound of the studied optimization problem.

Off-Policy Actor-Critic (Off-PAC) methods have proven successful in a variety of continuous control tasks. Normally, the critic's action-value function is updated using temporal-difference, and the critic in turn provides a loss for the actor that trains it to take actions with higher expected return. In this paper, we introduce a novel and flexible meta-critic that observes the learning process and meta-learns an additional loss for the actor that accelerates and improves actor-critic learning. Compared to the vanilla critic, the meta-critic network is explicitly trained to accelerate the learning process; and compared to existing meta-learning algorithms, meta-critic is rapidly learned online for a single task, rather than slowly over a family of tasks. Crucially, our meta-critic framework is designed for off-policy based learners, which currently provide state-of-the-art reinforcement learning sample efficiency. We demonstrate that online meta-critic learning leads to improvements in avariety of continuous control environments when combined with contemporary Off-PAC methods DDPG, TD3 and the state-of-the-art SAC.

We hypothesize that curiosity is a mechanism found by evolution that encourages meaningful exploration early in an agent's life in order to expose it to experiences that enable it to obtain high rewards over the course of its lifetime. We formulate the problem of generating curious behavior as one of meta-learning: an outer loop will search over a space of curiosity mechanisms that dynamically adapt the agent's reward signal, and an inner loop will perform standard reinforcement learning using the adapted reward signal. However, current meta-RL methods based on transferring neural network weights have only generalized between very similar tasks. To broaden the generalization, we instead propose to meta-learn algorithms: pieces of code similar to those designed by humans in ML papers. Our rich language of programs combines neural networks with other building blocks such as buffers, nearest-neighbor modules and custom loss functions. We demonstrate the effectiveness of the approach empirically, finding two novel curiosity algorithms that perform on par or better than human-designed published curiosity algorithms in domains as disparate as grid navigation with image inputs, acrobot, lunar lander, ant and hopper.

Meta-learning algorithms can accelerate the model-based reinforcement learning (MBRL) algorithms by finding an initial set of parameters for the dynamical model such that the model can be trained to match the actual dynamics of the system with only a few data-points. However, in the real world, a robot might encounter any situation starting from motor failures to finding itself in a rocky terrain where the dynamics of the robot can be significantly different from one another. In this paper, first, we show that when meta-training situations (the prior situations) have such diverse dynamics, using a single set of meta-trained parameters as a starting point still requires a large number of observations from the real system to learn a useful model of the dynamics. Second, we propose an algorithm called FAMLE that mitigates this limitation by meta-training several initial starting points (i.e., initial parameters) for training the model and allows the robot to select the most suitable starting point to adapt the model to the current situation with only a few gradient steps. We compare FAMLE to MBRL, MBRL with a meta-trained model with MAML, and model-free policy search algorithm PPO for various simulated and real robotic tasks, and show that FAMLE allows the robots to adapt to novel damages in significantly fewer time-steps than the baselines.

Automatic Curriculum Learning (ACL) has become a cornerstone of recent successes in Deep Reinforcement Learning (DRL).These methods shape the learning trajectories of agents by challenging them with tasks adapted to their capacities. In recent years, they have been used to improve sample efficiency and asymptotic performance, to organize exploration, to encourage generalization or to solve sparse reward problems, among others. The ambition of this work is dual: 1) to present a compact and accessible introduction to the Automatic Curriculum Learning literature and 2) to draw a bigger picture of the current state of the art in ACL to encourage the cross-breeding of existing concepts and the emergence of new ideas.