Geometry of Neural Reinforcement Learning in Continuous State and Action Spaces
By: Saket Tiwari, Omer Gottesman, George Konidaris
Potential Business Impact:
Makes robots learn faster by simplifying their movements.
Advances in reinforcement learning (RL) have led to its successful application in complex tasks with continuous state and action spaces. Despite these advances in practice, most theoretical work pertains to finite state and action spaces. We propose building a theoretical understanding of continuous state and action spaces by employing a geometric lens to understand the locally attained set of states. The set of all parametrised policies learnt through a semi-gradient based approach induces a set of attainable states in RL. We show that the training dynamics of a two-layer neural policy induce a low dimensional manifold of attainable states embedded in the high-dimensional nominal state space trained using an actor-critic algorithm. We prove that, under certain conditions, the dimensionality of this manifold is of the order of the dimensionality of the action space. This is the first result of its kind, linking the geometry of the state space to the dimensionality of the action space. We empirically corroborate this upper bound for four MuJoCo environments and also demonstrate the results in a toy environment with varying dimensionality. We also show the applicability of this theoretical result by introducing a local manifold learning layer to the policy and value function networks to improve the performance in control environments with very high degrees of freedom by changing one layer of the neural network to learn sparse representations.
Similar Papers
The Geometry of Abstraction: Continual Learning via Recursive Quotienting
Machine Learning (CS)
Helps computers remember everything without forgetting.
Emergent Riemannian geometry over learning discrete computations on continuous manifolds
Machine Learning (CS)
Helps computers learn to make decisions from pictures.
Offline Reinforcement Learning in Large State Spaces: Algorithms and Guarantees
Machine Learning (CS)
Teaches computers to learn from past mistakes.