Related papers: Behavior-Guided Actor-Critic: Improving Exploratio…
Humans sometimes choose actions that they themselves can identify as sub-optimal, or wrong, even in the absence of additional information. How is this possible? We present an algorithmic theory of metacognition based on a well-understood…
Standard deep reinforcement learning algorithms use a shared representation for the policy and value function, especially when training directly from images. However, we argue that more information is needed to accurately estimate the value…
Pretraining with expert demonstrations have been found useful in speeding up the training process of deep reinforcement learning algorithms since less online simulation data is required. Some people use supervised learning to speed up the…
In reinforcement learning (RL), function approximation errors are known to easily lead to the Q-value overestimations, thus greatly reducing policy performance. This paper presents a distributional soft actor-critic (DSAC) algorithm, which…
Deep reinforcement learning has made significant progress in robotic manipulation tasks and it works well in the ideal disturbance-free environment. However, in a real-world environment, both internal and external disturbances are…
While deep reinforcement learning has achieved tremendous successes in various applications, most existing works only focus on maximizing the expected value of total return and thus ignore its inherent stochasticity. Such stochasticity is…
We discuss the problem of decentralized multi-agent reinforcement learning (MARL) in this work. In our setting, the global state, action, and reward are assumed to be fully observable, while the local policy is protected as privacy by each…
Real-world applications require RL algorithms to act safely. During learning process, it is likely that the agent executes sub-optimal actions that may lead to unsafe/poor states of the system. Exploration is particularly brittle in…
A variety of theoretically-sound policy gradient algorithms exist for the on-policy setting due to the policy gradient theorem, which provides a simplified form for the gradient. The off-policy setting, however, has been less clear due to…
Policy gradient methods have become popular in multi-agent reinforcement learning, but they suffer from high variance due to the presence of environmental stochasticity and exploring agents (i.e., non-stationarity), which is potentially…
Policy gradient algorithms typically combine discounted future rewards with an estimated value function, to compute the direction and magnitude of parameter updates. However, for most Reinforcement Learning tasks, humans can provide…
Uncertainty quantification has been extensively used as a means to achieve efficient directed exploration in Reinforcement Learning (RL). However, state-of-the-art methods for continuous actions still suffer from high sample complexity…
Value-based methods of multi-agent reinforcement learning (MARL), especially the value decomposition methods, have been demonstrated on a range of challenging cooperative tasks. However, current methods pay little attention to the…
The actor-critic RL is widely used in various robotic control tasks. By viewing the actor-critic RL from the perspective of variational inference (VI), the policy network is trained to obtain the approximate posterior of actions given the…
Multi-agent reinforcement learning (MARL) has attracted much research attention recently. However, unlike its single-agent counterpart, many theoretical and algorithmic aspects of MARL have not been well-understood. In this paper, we study…
We propose a new objective, the counterfactual objective, unifying existing objectives for off-policy policy gradient algorithms in the continuing reinforcement learning (RL) setting. Compared to the commonly used excursion objective, which…
We reformulate the option framework as two parallel augmented MDPs. Under this novel formulation, all policy optimization algorithms can be used off the shelf to learn intra-option policies, option termination conditions, and a master…
Continuous control Deep Reinforcement Learning (RL) approaches are known to suffer from estimation biases, leading to suboptimal policies. This paper introduces innovative methods in RL, focusing on addressing and exploiting estimation…
In this paper, we propose actor-director-critic, a new framework for deep reinforcement learning. Compared with the actor-critic framework, the director role is added, and action classification and action evaluation are applied…
To learn approximately optimal acting policies for decision problems, modern Actor Critic algorithms rely on deep Neural Networks (DNNs) to parameterize the acting policy and greedification operators to iteratively improve it. The reliance…