In this paper, we study how we can develop HRL algorithms that are general, in that they do not make onerous additional assumptions beyond standard RL algorithms, and efficient, in the sense that they can be used with modest numbers of interaction samples, making them suitable for real-world problems such as robotic control.
Hierarchical Reinforcement Learning reinforcement-learning +1
We study the problem of representation learning in goal-conditioned hierarchical reinforcement learning.
Our cell achieves a test set perplexity of 62. 4 on the Penn Treebank, which is 3. 6 perplexity better than the previous state-of-the-art model.
We establish a new connection between value and policy based reinforcement learning (RL) based on a relationship between softmax temporal value consistency and policy optimality under entropy regularization.
Integrating model-free and model-based approaches in reinforcement learning has the potential to achieve the high performance of model-free algorithms with low sample complexity.
The popular Q-learning algorithm is known to overestimate action values under certain conditions.
Ranked #10 on Atari Games on Atari 2600 Gopher
We present the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning.
Ranked #1 on Atari Games on Atari 2600 Pong
In recent years there have been many successes of using deep representations in reinforcement learning.
Ranked #1 on Atari Games on Atari 2600 Pong
Bootstrapping is a core mechanism in Reinforcement Learning (RL).
Ranked #9 on Atari Games on Atari-57
Reinforcement learning (RL) algorithms involve the deep nesting of highly irregular computation patterns, each of which typically exhibits opportunities for distributed computation.