Bayesian reinforcement learning (BRL) offers a decision-theoretic solution to the problem of reinforcement learning. However, typical model-based BRL algorithms have focused either on ma intaining a posterior distribution on models or value functions and combining this with approx imate dynamic programming or tree search. This paper describes a novel backwards induction pri nciple for performing joint Bayesian estimation of models and value functions, from which many new BRL algorithms can be obtained. We demonstrate this idea with algorithms and experiments in discrete state spaces.

Can simple algorithms with a good representation solve challenging reinforcement learning problems? In this work, we answer this question in the affirmative, where we take "simple learning algorithm" to be tabular Q-Learning, the "good representations" to be a learned state abstraction, and "challenging problems" to be continuous control tasks. Our main contribution is a learning algorithm that abstracts a continuous state-space into a discrete one. We transfer this learned representation to unseen problems to enable effective learning. We provide theory showing that learned abstractions maintain a bounded value loss, and we report experiments showing that the abstractions empower tabular Q-Learning to learn efficiently in unseen tasks.

Recent researches show that machine learning has the potential to learn better heuristics than the one designed by human for solving combinatorial optimization problems. The deep neural network is used to characterize the input instance for constructing a feasible solution incrementally. Recently, an attention model is proposed to solve routing problems. In this model, the state of an instance is represented by node features that are fixed over time. However, the fact is, the state of an instance is changed according to the decision that the model made at different construction steps, and the node features should be updated correspondingly. Therefore, this paper presents a dynamic attention model with dynamic encoder-decoder architecture, which enables the model to explore node features dynamically and exploit hidden structure information effectively at different construction steps. This paper focuses on a challenging NP-hard problem, vehicle routing problem. The experiments indicate that our model outperforms the previous methods and also shows a good generalization performance.

The AI community has a long-term goal of building intelligent machines that interact effectively with the physical world, and a key challenge is teaching these systems to navigate through complex, unfamiliar real-world environments to reach a specified destination -- without a preprovided map. We are announcing today that Facebook AI has created a new large-scale distributed reinforcement learning (RL) algorithm called DD-PPO, which has effectively solved the task of point-goal navigation using only an RGB-D camera, GPS, and compass data. Agents trained with DD-PPO (which stands for decentralized distributed proximal policy optimization) achieve nearly 100 percent success in a variety of virtual environments, such as houses and office buildings. We have also successfully tested our model with tasks in real-world physical settings using a LoCoBot and Facebook AI's PyRobot platform. An unfortunate fact about maps is that they become outdated the moment they are created.

This chapter studies emerging cyber-attacks on reinforcement learning (RL) and introduces a quantitative approach to analyze the vulnerabilities of RL. Focusing on adversarial manipulation on the cost signals, we analyze the performance degradation of TD($\lambda$) and $Q$-learning algorithms under the manipulation. For TD($\lambda$), the approximation learned from the manipulated costs has an approximation error bound proportional to the magnitude of the attack. The effect of the adversarial attacks on the bound does not depend on the choice of $\lambda$. In $Q$-learning, we show that $Q$-learning algorithms converge under stealthy attacks and bounded falsifications on cost signals. We characterize the relation between the falsified cost and the $Q$-factors as well as the policy learned by the learning agent which provides fundamental limits for feasible offensive and defensive moves. We propose a robust region in terms of the cost within which the adversary can never achieve the targeted policy. We provide conditions on the falsified cost which can mislead the agent to learn an adversary's favored policy. A case study of TD($\lambda$) learning is provided to corroborate the results.

This paper presents a distributionally robust Q-Learning algorithm (DrQ) which leverages Wasserstein ambiguity sets to provide probabilistic out-of-sample safety guarantees during online learning. First, we follow past work by separating the constraint functions from the principal objective to create a hierarchy of machines within the constrained Markov decision process (CMDP). DrQ works within this framework by augmenting constraint costs with tightening offset variables obtained through Wasserstein distributionally robust optimization (DRO). These offset variables correspond to worst-case distributions of modeling error characterized by the TD-errors of the constraint Q-functions. This overall procedure allows us to safely approach the nominal constraint boundaries with strong probabilistic out-of-sample safety guarantees. Using a case study of safe lithium-ion battery fast charging, we demonstrate dramatic improvements in safety and performance relative to a conventional DQN.

This paper presents a hierarchical framework for Deep Reinforcement Learning that acquires motor skills for a variety of push recovery and balancing behaviors, i.e., ankle, hip, foot tilting, and stepping strategies. The policy is trained in a physics simulator with realistic setting of robot model and low-level impedance control that are easy to transfer the learned skills to real robots. The advantage over traditional methods is the integration of high-level planner and feedback control all in one single coherent policy network, which is generic for learning versatile balancing and recovery motions against unknown perturbations at arbitrary locations (e.g., legs, torso). Furthermore, the proposed framework allows the policy to be learned quickly by many state-of-the-art learning algorithms. By comparing our learned results to studies of preprogrammed, special-purpose controllers in the literature, self-learned skills are comparable in terms of disturbance rejection but with additional advantages of producing a wide range of adaptive, versatile and robust behaviors.

Exploration is widely regarded as one of the most challenging aspects of reinforcement learning (RL), with many naive approaches succumbing to exponential sample complexity. To isolate the challenges of exploration, we propose a new "reward-free RL" framework. In the exploration phase, the agent first collects trajectories from an MDP $\mathcal{M}$ without a pre-specified reward function. After exploration, it is tasked with computing near-optimal policies under for $\mathcal{M}$ for a collection of given reward functions. This framework is particularly suitable when there are many reward functions of interest, or when the reward function is shaped by an external agent to elicit desired behavior. We give an efficient algorithm that conducts $\tilde{\mathcal{O}}(S^2A\mathrm{poly}(H)/\epsilon^2)$ episodes of exploration and returns $\epsilon$-suboptimal policies for an arbitrary number of reward functions. We achieve this by finding exploratory policies that visit each "significant" state with probability proportional to its maximum visitation probability under any possible policy. Moreover, our planning procedure can be instantiated by any black-box approximate planner, such as value iteration or natural policy gradient. We also give a nearly-matching $\Omega(S^2AH^2/\epsilon^2)$ lower bound, demonstrating the near-optimality of our algorithm in this setting.

In batch reinforcement learning (RL), one often constrains a learned policy to be close to the behavior (data-generating) policy, e.g., by constraining the learned action distribution to differ from the behavior policy by some maximum degree that is the same at each state. This can cause batch RL to be overly conservative, unable to exploit large policy changes at frequently-visited, high-confidence states without risking poor performance at sparsely-visited states. To remedy this, we propose residual policies, where the allowable deviation of the learned policy is state-action-dependent. We derive a new for RL method, BRPO, which learns both the policy and allowable deviation that jointly maximize a lower bound on policy performance. We show that BRPO achieves the state-of-the-art performance in a number of tasks.

There is broad interest in creating RL agents that can solve many (related) tasks and adapt to new tasks and environments after initial training. Model-based RL leverages learned surrogate models that describe dynamics and rewards of individual tasks, such that planning in a good surrogate can lead to good control of the true system. Rather than solving each task individually from scratch, hierarchical models can exploit the fact that tasks are often related by (unobserved) causal factors of variation in order to achieve efficient generalization, as in learning how the mass of an item affects the force required to lift it can generalize to previously unobserved masses. We propose Generalized Hidden Parameter MDPs (GHP-MDPs) that describe a family of MDPs where both dynamics and reward can change as a function of hidden parameters that vary across tasks. The GHP-MDP augments model-based RL with latent variables that capture these hidden parameters, facilitating transfer across tasks. We also explore a variant of the model that incorporates explicit latent structure mirroring the causal factors of variation across tasks (for instance: agent properties, environmental factors, and goals). We experimentally demonstrate state-of-the-art performance and sample-efficiency on a new challenging MuJoCo task using reward and dynamics latent spaces, while beating a previous state-of-the-art baseline with $>10\times$ less data. Using test-time inference of the latent variables, our approach generalizes in a single episode to novel combinations of dynamics and reward, and to novel rewards.