Multitask Adaptation by Retrospective Exploration with Learned World Models

Model-based reinforcement learning (MBRL) allows solving complex tasks in a sample-efficient manner. However, no information is reused between the tasks. In this work, we propose a meta-learned addressing model called RAMa that provides training samples for the MBRL agent taken from continuously growing task-agnostic storage. The model is trained to maximize the expected agent's performance by selecting promising trajectories solving prior tasks from the storage. We show that such retrospective exploration can accelerate the learning process of the MBRL agent by better informing learned dynamics and prompting agent with exploratory trajectories. We test the performance of our approach on several domains from the DeepMind control suite, from Metaworld multitask benchmark, and from our bespoke environment implemented with a robotic NVIDIA Isaac simulator to test the ability of the model to act in a photorealistic, ray-traced environment.

Long-Term Exploration in Persistent MDPs

Exploration is an essential part of reinforcement learning, which restricts the quality of learned policy. Hard-exploration environments are defined by huge state space and sparse rewards. In such conditions, an exhaustive exploration of the environment is often impossible, and the successful training of an agent requires a lot of interaction steps. In this paper, we propose an exploration method called Rollback-Explore (RbExplore), which utilizes the concept of the persistent Markov decision process, in which agents during training can roll back to visited states. We test our algorithm in the hard-exploration Prince of Persia game, without rewards and domain knowledge. At all used levels of the game, our agent outperforms or shows comparable results with state-of-the-art curiosity methods with knowledge-based intrinsic motivation: ICM and RND. An implementation of RbExplore can be found at https://github.com/cds-mipt/RbExplore.

Landmark Policy Optimization for Object Navigation Task

This work studies object goal navigation task, which involves navigating to the closest object related to the given semantic category in unseen environments. Recent works have shown significant achievements both in the end-to-end Reinforcement Learning approach and modular systems, but need a big step forward to be robust and optimal. We propose a hierarchical method that incorporates standard task formulation and additional area knowledge as landmarks, with a way to extract these landmarks. In a hierarchy, a low level consists of separately trained algorithms to the most intuitive skills, and a high level decides which skill is needed at this moment. With all proposed solutions, we achieve a 0.75 success rate in a realistic Habitat simulator. After a small stage of additional model training in a reconstructed virtual area at a simulator, we successfully confirmed our results in a real-world case.

Q-Mixing Network for Multi-Agent Pathfinding in Partially Observable Grid Environments

In this paper, we consider the problem of multi-agent navigation in partially observable grid environments. This problem is challenging for centralized planning approaches as they, typically, rely on the full knowledge of the environment. We suggest utilizing the reinforcement learning approach when the agents, first, learn the policies that map observations to actions and then follow these policies to reach their goals. To tackle the challenge associated with learning cooperative behavior, i.e. in many cases agents need to yield to each other to accomplish a mission, we use a mixing Q-network that complements learning individual policies. In the experimental evaluation, we show that such approach leads to plausible results and scales well to large number of agents.

Delta Schema Network in Model-based Reinforcement Learning

This work is devoted to unresolved problems of Artificial General Intelligence - the inefficiency of transfer learning. One of the mechanisms that are used to solve this problem in the area of reinforcement learning is a model-based approach. In the paper we are expanding the schema networks method which allows to extract the logical relationships between objects and actions from the environment data. We present algorithms for training a Delta Schema Network (DSN), predicting future states of the environment and planning actions that will lead to positive reward. DSN shows strong performance of transfer learning on the classic Atari game environment.

Forgetful Experience Replay in Hierarchical Reinforcement Learning from Demonstrations

Currently, deep reinforcement learning (RL) shows impressive results in complex gaming and robotic environments. Often these results are achieved at the expense of huge computational costs and require an incredible number of episodes of interaction between the agent and the environment. There are two main approaches to improving the sample efficiency of reinforcement learning methods - using hierarchical methods and expert demonstrations. In this paper, we propose a combination of these approaches that allow the agent to use low-quality demonstrations in complex vision-based environments with multiple related goals. Our forgetful experience replay (ForgER) algorithm effectively handles errors in expert data and reduces quality losses when adapting the action space and states representation to the agent's capabilities. Our proposed goal-oriented structuring of replay buffer allows the agent to automatically highlight sub-goals for solving complex hierarchical tasks in demonstrations. Our method is universal and can be integrated into various off-policy methods. It surpasses all known existing state-of-the-art RL methods using expert demonstrations on various model environments. The solution based on our algorithm beats all the solutions for the famous MineRL competition and allows the agent to mine a diamond in the Minecraft environment.

Hierarchical Deep Q-Network from Imperfect Demonstrations in Minecraft

We present hierarchical Deep Q-Network with Forgetting (HDQF) that took first place in MineRL competition. HDQF works on imperfect demonstrations utilize hierarchical structure of expert trajectories extracting effective sequence of meta-actions and subgoals. We introduce structured task dependent replay buffer and forgetting technique that allow the HDQF agent to gradually erase poor-quality expert data from the buffer. In this paper we present the details of the HDQF algorithm and give the experimental results in Minecraft domain.

Hierarchical Deep Q-Network with Forgetting from Imperfect Demonstrations in Minecraft

We present hierarchical Deep Q-Network with Forgetting (HDQF) that took first place in MineRL competition. HDQF works on imperfect demonstrations utilize hierarchical structure of expert trajectories extracting effective sequence of meta-actions and subgoals. We introduce structured task dependent replay buffer and forgetting technique that allow the HDQF agent to gradually erase poor-quality expert data from the buffer. In this paper we present the details of the HDQF algorithm and give the experimental results in Minecraft domain.

Automatic formation of the structure of abstract machines in hierarchical reinforcement learning with state clustering

We introduce a new approach to hierarchy formation and task decomposition in hierarchical reinforcement learning. Our method is based on the Hierarchy Of Abstract Machines (HAM) framework because HAM approach is able to design efficient controllers that will realize specific behaviors in real robots. The key to our algorithm is the introduction of the internal or "mental" environment in which the state represents the structure of the HAM hierarchy. The internal action in this environment leads to changes the hierarchy of HAMs. We propose the classical Q-learning procedure in the internal environment which allows the agent to obtain an optimal hierarchy. We extends the HAM framework by adding on-model approach to select the appropriate sub-machine to execute action sequences for certain class of external environment states. Preliminary experiments demonstrated the prospects of the method.