CoBERL: Contrastive BERT for Reinforcement Learning
Many reinforcement learning (RL) agents require a large amount of experience to solve tasks. We propose Contrastive BERT for RL (CoBERL), an agent that combines a new contrastive loss and a hybrid LSTM-transformer architecture to tackle the challenge of improving data efficiency. CoBERL enables efficient, robust learning from pixels across a wide range of domains. We use bidirectional masked prediction in combination with a generalization of recent contrastive methods to learn better representations for transformers in RL, without the need of hand engineered data augmentations. We find that CoBERL consistently improves performance across the full Atari suite, a set of control tasks and a challenging 3D environment.
PDF Abstract ICML Workshop 2021 PDF ICML Workshop 2021 AbstractCode
Colab
Arcade Learning Environment
DeepMind Control Suite
Results from the Paper
Submit
results from this paper
to get state-of-the-art GitHub badges and help the
community compare results to other papers.
Methods
Adam •
Attention Dropout •
BERT •
CoBERL •
Dense Connections •
Dropout •
GELU •
GRU •
GTrXL •
Layer Normalization •
Linear Layer •
Linear Warmup With Linear Decay •
LSTM •
Multi-Head Attention •
Position-Wise Feed-Forward Layer •
ReLIC •
Residual Connection •
Scaled Dot-Product Attention •
Sigmoid Activation •
Softmax •
Tanh Activation •
Weight Decay •
WordPiece
