AIMAPP unifies online topological mapping, localisation, and planning under a single active-inference generative model for self-supervised robot navigation.
Learning to Navigate in Complex Environments
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
abstract
Learning to navigate in complex environments with dynamic elements is an important milestone in developing AI agents. In this work we formulate the navigation question as a reinforcement learning problem and show that data efficiency and task performance can be dramatically improved by relying on additional auxiliary tasks leveraging multimodal sensory inputs. In particular we consider jointly learning the goal-driven reinforcement learning problem with auxiliary depth prediction and loop closure classification tasks. This approach can learn to navigate from raw sensory input in complicated 3D mazes, approaching human-level performance even under conditions where the goal location changes frequently. We provide detailed analysis of the agent behaviour, its ability to localise, and its network activity dynamics, showing that the agent implicitly learns key navigation abilities.
representative citing papers
LEO enables efficient all-goals learning in goal-conditioned RL by jointly predicting for all goals in one network pass, yielding >250x speedup over relabelling and better performance on Craftax.
A curiosity-based 3D exploration policy that pairs persistent online 3D reconstruction with episodic sequence modeling over RGB to outperform active-mapping baselines on HM3D and transfer zero-shot to Gibson and synthetic worlds.
BMIL learns belief modules jointly with policies for GAIL-style imitation learning in POMDPs, outperforming separate training and standard GAIL on continuous control tasks.
Empirical comparison finds that self-supervised representations vary in capturing agent state and generalizing to new levels or textures depending on environment visuals and dynamics.
Multi-step predictive generative models form stable belief states capturing environment layout and agent pose, yielding higher data efficiency on RL tasks than model-free agents.
citing papers explorer
-
Online Structure Learning and Planning for Autonomous Robot Navigation using Active Inference
AIMAPP unifies online topological mapping, localisation, and planning under a single active-inference generative model for self-supervised robot navigation.
-
Goal-Conditioned Agents that Learn Everything All at Once
LEO enables efficient all-goals learning in goal-conditioned RL by jointly predicting for all goals in one network pass, yielding >250x speedup over relabelling and better performance on Craftax.
-
Remember to be Curious: Episodic Context and Persistent Worlds for 3D Exploration
A curiosity-based 3D exploration policy that pairs persistent online 3D reconstruction with episodic sequence modeling over RGB to outperform active-mapping baselines on HM3D and transfer zero-shot to Gibson and synthetic worlds.
-
Learning Belief Representations for Imitation Learning in POMDPs
BMIL learns belief modules jointly with policies for GAIL-style imitation learning in POMDPs, outperforming separate training and standard GAIL on continuous control tasks.
-
Supervise Thyself: Examining Self-Supervised Representations in Interactive Environments
Empirical comparison finds that self-supervised representations vary in capturing agent state and generalizing to new levels or textures depending on environment visuals and dynamics.
-
Shaping Belief States with Generative Environment Models for RL
Multi-step predictive generative models form stable belief states capturing environment layout and agent pose, yielding higher data efficiency on RL tasks than model-free agents.