V ARIBAD: A V ERY G OOD M ETHOD FOR B AYES-A DAPTIVE D EEP RL VIA M ETA-L EARNING Luisa Zintgraf University of Oxford Kyriacos Shiarlis Latent Logic Maximilian Igl University of Oxford Sebastian Schulze University of Oxford Y arin Gal OA TML Group, University of Oxford Katja Hofmann Microsoft Research Shimon Whiteson University of Oxford Latent Logic A BSTRACT Trading off exploration and exploitation in an unknown environment is key to maximising expected return during learning. A Bayes-optimal policy, which does so optimally, conditions its actions not only on the environment state but on the agent's uncertainty about the environment. Computing a Bayes-optimal policy is however intractable for all but the smallest tasks. In this paper, we introduce variational Bayes-Adaptive Deep RL (variBAD), a way to meta-learn to perform approximate inference in an unknown environment, and incorporate task uncertainty directly during action selection. In a grid-world domain, we illustrate how variBAD performs structured online exploration as a function of task uncertainty. We also evaluate variBAD on MuJoCo domains widely used in meta-RL and show that it achieves higher return during training than existing methods. 1 I NTRODUCTION Reinforcement learning (RL) is typically concerned with finding an optimal policy that maximises expected return for a given Markov decision process (MDP) with an unknown reward and transition function. If these were known, the optimal policy could in theory be computed without interacting with the environment. By contrast, learning in an unknown environment typically requires trading off exploration (learning about the environment) and exploitation (taking promising actions). Balancing this tradeoff is key to maximising expected return during learning . A Bayes-optimal policy, which does so optimally, conditions actions not only on the environment state but on the agent's own uncertainty about the current MDP . In principle, a Bayes-optimal policy can be computed using the framework of Bayes-adaptive Markov decision processes (BAMDPs) (Martin, 1967; Duff & Barto, 2002). The agent maintains a belief, i.e., a posterior distribution, over possible environments. Augmenting the state space of the underlying MDP with this posterior distribution yields a BAMDP, a special case of a belief MDP (Kaelbling et al., 1998).

We present Multitask Soft Option Learning (MSOL), a hierarchical multitask framework based on Planning as Inference. MSOL extends the concept of options, using separate variational posteriors for each task, regularized by a shared prior. This allows fine-tuning of options for new tasks without forgetting their learned policies, leading to faster training without reducing the expressiveness of the hierarchical policy. Additionally, MSOL avoids several instabilities during training in a multitask setting and provides a natural way to not only learn intra-option policies, but also their terminations. We demonstrate empirically that MSOL significantly outperforms both hierarchical and flat transfer-learning baselines in challenging multi-task environments.

We provide theoretical and empirical evidence that using tighter evidence lower bounds (ELBOs) can be detrimental to the process of learning an inference network by reducing the signal-to-noise ratio of the gradient estimator. Our results call into question common implicit assumptions that tighter ELBOs are better variational objectives for simultaneous model learning and inference amortization schemes. Based on our insights, we introduce three new algorithms: the partially importance weighted auto-encoder (PIWAE), the multiply importance weighted auto-encoder (MIWAE), and the combination importance weighted auto-encoder (CIWAE), each of which includes the standard importance weighted auto-encoder (IWAE) as a special case. We show that each can deliver improvements over IWAE, even when performance is measured by the IWAE target itself. Furthermore, our results suggest that PIWAE may be able to deliver simultaneous improvements in the training of both the inference and generative networks.

Many real-world sequential decision making problems are partially observable by nature, and the environment model is typically unknown. Consequently, there is great need for reinforcement learning methods that can tackle such problems given only a stream of incomplete and noisy observations. In this paper, we propose deep variational reinforcement learning (DVRL), which introduces an inductive bias that allows an agent to learn a generative model of the environment and perform inference in that model to effectively aggregate the available information. We develop an n-step approximation to the evidence lower bound (ELBO), allowing the model to be trained jointly with the policy. This ensures that the latent state representation is suitable for the control task. In experiments on Mountain Hike and flickering Atari we show that our method outperforms previous approaches relying on recurrent neural networks to encode the past.

We introduce AESMC: a method for using deep neural networks for simultaneous model learning and inference amortization in a broad family of structured probabilistic models. Starting with an unlabeled dataset and a partially specified underlying generative model, AESMC refines the generative model and learns efficient proposal distributions for SMC for performing inference in this model. Our approach relies on 1) efficiency of SMC in performing inference in structured probabilistic models and 2) flexibility of deep neural networks to model complex conditional probability distributions. We demonstrate that our approach provides a fast, accurate, easy-to-implement, and scalable means for carrying out parameter estimation in high-dimensional statistical models as well as simultaneous model learning and proposal amortization in neural network based models.