Walk the Random Walk: Learning to Discover and Reach Goals Without Supervision
Learning a diverse set of skills by interacting with an environment without any external supervision is an important challenge. In particular, obtaining a goal-conditioned agent that can reach any given state is useful in many applications. We propose a novel method for training such a goal-conditioned agent without any external rewards or any domain knowledge. We use random walk to train a reachability network that predicts the similarity between two states. This reachability network is then used in building goal memory containing past observations that are diverse and well-balanced. Finally, we train a goal-conditioned policy network with goals sampled from the goal memory and reward it by the reachability network and the goal memory. All the components are kept updated throughout training as the agent discovers and learns new goals. We apply our method to a continuous control navigation and robotic manipulation tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
continuous-controlContinuous ControlSimilar Papers 제목 키워드 기반
Weisfeiler and Leman Go Walking: Random Walk Kernels Revisited
Random walk kernels have been introduced in seminal work on graph learning and were later largely superseded by kernels based on the Weisfeiler-Leman test for graph isomorphism. We give a unified view on both classes of …
Graph LearningDiscovering Intrinsic Reward with Contrastive Random Walk
The aim of this paper is to demonstrate the efficacy of using Contrastive Random Walk as a curiosity method to achieve faster convergence to the optimal policy.Contrastive Random Walk defines the transition matrix of a r…
Revisiting Random Walks for Learning on Graphs
We revisit a simple idea for machine learning on graphs, where a random walk on a graph produces a machine-readable record, and this record is processed by a deep neural network to directly make vertex-level or graph-lev…
Language ModellingExpected Runtime Comparisons Between Breadth-First Search and Constant-Depth Restarting Random Walks
When greedy search algorithms encounter a local minima or plateau, the search typically devolves into a breadth-first search (BrFS), or a local search technique is used in an attempt to find a way out. In this work, we f…
Degree-Based Random Walk Approach for Graph Embedding
Graph embedding, representing local and global neighborhood information by numerical vectors, is a crucial part of the mathematical modeling of a wide range of real-world systems. Among the embedding algorithms, random w…
Graph EmbeddingLink PredictionNode Classification