References Generative Adversarial Imitation Learning Time-Contrastive Networks: Self-Supervised Learning from Multi-View Observation One-Shot Visual Imitation Learning via Meta-Learning Learning to Search via Self-Imitation

We study the problem of learning a good search policy. To do so, we propose the self-imitation learning setting, which builds upon imitation learning in two ways. First, self-imitation uses feedback provided by retrospective analysis of demonstrated search traces. Second, the policy can learn from its own decisions and mistakes without requiring repeated feedback from an external expert. Combined, these two properties allow our approach to iteratively scale up to larger problem sizes than the initial problem size for which expert demonstrations were provided. We showcase the effectiveness of our approach on a synthetic maze solving task and the problem of risk-aware path planning. Zero-Shot Visual Imitation

n our framework, the role of the expert is only to communicate the goals (i.e., what to imitate) during inference. The learned policy is then employed to mimic the expert (i.e., how to imitate) after seeing just a sequence of images demonstrating the desired task. Our method is 'zero-shot' in the sense that the agent never has access to expert actions during training or for the task demonstration at inference Playing hard exploration games by watching YouTube

Deep reinforcement learning methods traditionally struggle with tasks where environment rewards are particularly sparse. One successful method of guiding exploration in these domains is to imitate trajectories provided by a human demonstrator. However, these demonstrations are typically collected under artificial conditions, i.e. with access to the agent's exact environment setup and the demonstrator's action and reward trajectories. Here we propose a two-stage method that overcomes these limitations by relying on noisy, unaligned footage without access to such data. First, we learn to map unaligned videos from multiple sources to a common representation using self-supervised objectives constructed over both time and modality (i.e. vision and sound). Second, we embed a single YouTube video in this representation to construct a reward function that encourages an agent to imitate human gameplay. This method of one-shot imitation allows our agent to convincingly exceed human-level performance on the infamously hard exploration games Montezuma's Revenge, Pitfall! and Private Eye for the first time, even if the agent is not presented with any environment rewards. A neural network trained to predict future video frames mimics critical properties of biological neuronal responses and perception

we study the emergent properties of a previously-described recurrent generative network that is trained to predict future video frames in a self-supervised manner. Remarkably, the model is able to capture a wide variety of seemingly disparate phenomena observed in visual cortex, ranging from single unit response dynamics to complex perceptual motion illusions. These results suggest potentially deep connections between recurrent predictive neural network models and the brain, providing new leads that can enrich both fields. Inspiration Learning through Preferences

Current imitation learning techniques are too restrictive because they require the agent and expert to share the same action space. However, oftentimes agents that act differently from the expert can solve the task just as good. For example, a person lifting a box can be imitated by a ceiling mounted robot or a desktop-based robotic-arm. In both cases, the end goal of lifting the box is achieved, perhaps using different strategies. We denote this setup as \textit{Inspiration Learning} - knowledge transfer between agents that operate in different action spaces. Since state-action expert demonstrations can no longer be used, Inspiration learning requires novel methods to guide the agent towards the end goal. In this work, we rely on ideas of Preferential based Reinforcement Learning (PbRL) to design Advantage Actor-Critic algorithms for solving inspiration learning tasks. Unlike classic actor-critic architectures, the critic we use consists of two parts: a) a state-value estimation as in common actor-critic algorithms and b) a single step reward function derived from an expert/agent classifier. We show that our method is capable of extending the current imitation framework to new horizons. This includes continuous-to-discrete action imitation, as well as primitive-to-macro action imitation. Hierarchical Imitation and Reinforcement Learning

We propose an algorithmic framework, called hierarchical guidance, that leverages the hierarchical structure of the underlying problem to integrate different modes of expert interaction. Our framework can incorporate different combinations of imitation learning (IL) and reinforcement learning (RL) at different levels, leading to dramatic reductions in both expert effort and cost of exploration. ONE-SHOT HIGH-FIDELITY IMITATION: TRAINING LARGE-SCALE DEEP NETS WITH RL

In this paper, we introduce an off-policy RL algorithm (MetaMimic) to narrow this gap. MetaMimic can learn both (i) policies for high-fidelity one-shot imitation of diverse novel skills, and (ii) policies that enable the agent to solve tasks more efficiently than the demonstrators. MetaMimic relies on the principle of storing all experiences in a memory and replaying these to learn massive deep neural network policies by off-policy RL. Supervising strong learners by amplifying weak experts

We propose Iterated Amplification, an alternative training strategy which progressively builds up a training signal for difficult problems by combining solutions to easier subproblems. Iterated Amplification is closely related to Expert Iteration (Anthony et al., 2017; Silver et al., 2017), except that it uses no external reward function. Learning Beam Search Policies via Imitation Learning

Beam search is widely used for approximate decoding in structured prediction problems. Models often use a beam at test time but ignore its existence at train time, and therefore do not explicitly learn how to use the beam. We develop an unifying meta-algorithm for learning beam search policies using imitation learning. In our setting, the beam is part of the model, and not just an artifact of approximate decoding. Our meta-algorithm captures existing learning algorithms and suggests new ones. It also lets us show novel no-regret guarantees for learning beam search policies. Learning from Demonstration in the Wild HG-DAgger: Interactive Imitation Learning with Human Experts Neural probabilistic motor primitives for humanoid control Playing hard exploration games by watching YouTube