Reinforcement Learning
Robust Knowledge Transfer in Tiered RL
We identify a natural and necessary condition called the "Optimal
a3621ee907def47c1b952ade25c67698-Paper-Conference.pdf
This paper explores the potential of building scalable techniques to facilitate autonomous cooperation among communicative agents, and provides insight into their "cognitive" processes. To address the challenges of achieving autonomous cooperation, we propose a novel communicative agent framework named roleplaying .
Learning to Assist Humans without Inferring Rewards
Assistive agents should make humans' lives easier.
A Proof Proof of Proposition 4.2 Proposition 4.2 The performance gap of evaluating policy profile (π, µ) and (π, π
Proof of Theorem 4.7 We first prove a Lemma. Theorem A.2. (Theorem 1 in [36]) Let ϵ = max Theorem 4.7 In a two-player game, suppose that According to Theorem A.2, we have J ( π, µ) J ( π, α) E CQL [20] puts regularization on the learning of Q function to penalize out-of-distribution actions. The CSP algorithm is illustrated in Algorithm 1. The proxy model is trained adversarially against our agent, therefore, we set the proxy's reward function to be the negative of our agent's reward. We show experiment details of the Maze example in this section.
We introduce a novel framework for analyzing reinforcement learning (RL) in continuous state-action spaces, and use it to prove fast rates of convergence in both
We argue that these properties are satisfied in many continuous state-action Markov decision processes.
The Ladder in Chaos: Improving Policy Learning by Harnessing the Parameter Evolving Path in A Low-dimensional Space Hongyao Tang
Deep Reinforcement Learning (DRL) is far from well understood, although its great potential has been demonstrated with a lot of achievements in different practical problems [Badia et al., 2020, Shah et al., 2022, Fawzi et al., 2022, Degrave et al., 2022, OpenAI, 2022]. Consistent efforts are made to gain a better understanding of the learning dynamics of RL agents.
Information Maximizing Curriculum: A Curriculum-Based Approach for Imitating Diverse Skills Denis Blessing
Imitation learning uses data for training policies to solve complex tasks.
