Policy Gradient Critics

19 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Memory-based control with recurrent neural networks (2015, methodology): “[30] trained LSTM-based stochastic policies using Reinforce; [31, 29, 32] used actor-critic architectures.”
Sequential Constant Size Compressors for Reinforcement Learning (2011, methodology): “Recurrent Policy Gradients and Policy Gradient Critics [25] can be used to train RNN such as LSTM [10] — these significantly outperformed other single-agent methods on several difficult deep memory RL benchmark tasks.”
Driven by Compression Progress: A Simple Principle Explains Essential Aspects of Subjective Beauty, Novelty, Surprise, Interestingness, Attention, Curiosity, Creativity, Art, Science, Music, Jokes (2008, methodology): “…efﬁciently, without frequent expensive compressor performance evaluations on the entire history so far; (3) study the applicability of recent improved RL techniques in the ﬁelds of policy gradients [110, 119, 118, 56, 100, 117], artiﬁcial evolution [43, 20, 21, 19, 22, 23, 24], and others [71, 75].”
Autonomous Navigation of UAVs in Large-Scale Complex Environments: A Deep Reinforcement Learning Approach (2019, methodology): “Of these methods, policy gradient methods such as likelihood-ratio methods [29], [30] and actor-critic methods [31], [32] derive parameterized stochastic policies for model-free POMDPs with continuous action spaces by performing gradient descent in the parameter space.”