Progressive Reinforcement Learning with Distillation for Multi-Skilled Motion Control

02/13/2018
by   Glen Berseth, et al.
0

Deep reinforcement learning has demonstrated increasing capabilities for continuous control problems, including agents that can move with skill and agility through their environment. An open problem in this setting is that of developing good strategies for integrating or merging policies for multiple skills, where each individual skill is a specialist in a specific skill and its associated state distribution. We extend policy distillation methods to the continuous action setting and leverage this technique to combine expert policies, as evaluated in the domain of simulated bipedal locomotion across different classes of terrain. We also introduce an input injection method for augmenting an existing policy network to exploit new input features. Lastly, our method uses transfer learning to assist in the efficient acquisition of new skills. The combination of these methods allows a policy to be incrementally augmented with new skills. We compare our progressive learning and integration via distillation (PLAID) method against three alternative baselines.

READ FULL TEXT

page 7

page 13

page 14

research
12/29/2019

Real-time Policy Distillation in Deep Reinforcement Learning

Policy distillation in deep reinforcement learning provides an effective...
research
11/24/2022

SkillS: Adaptive Skill Sequencing for Efficient Temporally-Extended Exploration

The ability to effectively reuse prior knowledge is a key requirement wh...
research
09/08/2023

Subwords as Skills: Tokenization for Sparse-Reward Reinforcement Learning

Exploration in sparse-reward reinforcement learning is difficult due to ...
research
10/05/2022

Neural Distillation as a State Representation Bottleneck in Reinforcement Learning

Learning a good state representation is a critical skill when dealing wi...
research
06/27/2012

Learning Parameterized Skills

We introduce a method for constructing skills capable of solving tasks d...
research
08/14/2019

Skill Transfer in Deep Reinforcement Learning under Morphological Heterogeneity

Transfer learning methods for reinforcement learning (RL) domains facili...
research
12/05/2018

Entropic Policy Composition with Generalized Policy Improvement and Divergence Correction

Deep reinforcement learning (RL) algorithms have made great strides in r...

Please sign up or login with your details

Forgot password? Click here to reset