Temporal Transfer Learning selects source tasks for zero-shot transfer of RL policies to solve a range of coarse-grained advisory autonomy hold durations in traffic optimization more reliably than baselines.
DARLA: Improving Zero-Shot Transfer in Reinforcement Learning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
Domain adaptation is an important open problem in deep reinforcement learning (RL). In many scenarios of interest data is hard to obtain, so agents may learn a source policy in a setting where data is readily available, with the hope that it generalises well to the target domain. We propose a new multi-stage RL agent, DARLA (DisentAngled Representation Learning Agent), which learns to see before learning to act. DARLA's vision is based on learning a disentangled representation of the observed environment. Once DARLA can see, it is able to acquire source policies that are robust to many domain shifts - even with no access to the target domain. DARLA significantly outperforms conventional baselines in zero-shot domain adaptation scenarios, an effect that holds across a variety of RL environments (Jaco arm, DeepMind Lab) and base RL algorithms (DQN, A3C and EC).
fields
cs.RO 2representative citing papers
citing papers explorer
-
Temporal Transfer Learning for Traffic Optimization with Coarse-grained Advisory Autonomy
Temporal Transfer Learning selects source tasks for zero-shot transfer of RL policies to solve a range of coarse-grained advisory autonomy hold durations in traffic optimization more reliably than baselines.
- State-Conditional Adversarial Learning: An Off-Policy Visual Domain Transfer Method for End-to-End Imitation Learning