meta-learning-34c67f1f·2 events·first seen Aliases: meta-learning
OpenAI published research on one-shot imitation learning, a technique enabling agents to learn new tasks from a single demonstration. The approach allows a policy network to observe a demonstration and immediately generalize to new instances of the same task without additional training. This was an early contribution to the field of meta-learning and few-shot generalization in robotics and sequential decision-making.
OpenAI released Evolved Policy Gradients (EPG), a meta-learning method that evolves the loss function used to train reinforcement learning agents rather than hand-designing it. The approach enables faster adaptation to novel tasks, with agents demonstrating generalization to test-time scenarios outside their training distribution, such as navigating to objects placed in new locations. EPG represents an experimental direction in automated algorithm discovery for RL.