11 accepted papers
To date, distributional reinforcement learning (distributional RL) methods have exclusively focused on the discounted setting, where an agent aims to optimize a discounted sum of rewards over time. In this work, we extend distributional RL to the average-reward setting, where an agent aims to optimi
Current state-of-the-art methods for out-of-distribution (OOD) generalization lack the ability to effectively address datasets with heterogeneous causal subgraphs at the instance level. Existing approaches that attempt to handle such heterogeneity either rely on data augmentation, which risks alteri…
Time series observations can be seen as realizations of an underlying dynamical system governed by rules that we typically do not know. For time series learning tasks we create our model using available data. Training on available realizations, where data is limited, often induces severe over-fittin…
We propose a new transfer learning algorithm between tasks with different dynamics. The proposed algorithm solves an Imitation from Observation problem (IfO) to ground the source environment to the target task before learning an optimal policy in the grounded environment. The learned policy is deplo…
We focus on multiple experts performing a task in a Markov decision process (MDP) environment. A probabilistic assignment of trajectories to clusters and a mathematical framework which leverages the utility function are employed to jointly estimate the discount factor and reward. We treat the number…
Learning from Demonstrations (LfD) is a powerful approach for incorporating advice from experts in the form of demonstrations. However, demonstrations often come from multiple sub-optimal experts with conflicting goals, rendering them difficult to incorporate effectively in online settings. To addre…
In reinforcement learning, agents that consider the context or current state when transferring source policies have been shown to outperform context-free approaches. However, existing approaches suffer from limitations, including sensitivity to sparse or delayed rewards and estimation errors in valu…
The capability of incrementally learning new tasks without forgetting old ones is a challenging problem due to catastrophic forgetting. This challenge becomes greater when novel tasks contain very few labelled training samples. Currently, most methods are dedicated to class-incremental learning and…
Sample efficiency and risk-awareness are central to the development of practical reinforcement learning (RL) for complex decision-making. The former can be addressed by transfer learning, while the latter by optimizing some utility function of the return. However, the problem of transferring skills…
Resolving the exploration-exploitation trade-off remains a fundamental problem in the design and implementation of reinforcement learning (RL) algorithms. In this paper, we focus on model-free RL using the epsilon-greedy exploration policy, which despite its simplicity, remains one of the most frequ…
Potential based reward shaping is a powerful technique for accelerating convergence of reinforcement learning algorithms. Typically, such information includes an estimate of the optimal value function and is often provided by a human expert or other sources of domain knowledge. However, this informa…