Recent advancements in differential simulators offer a promising approach to enhancing the sim2real transfer of reinforcement learning (RL) agents by enabling the computation of gradients of the simulator’s dynamics with respect to its parameters. However, the application of these gradients is often limited to specific scenarios. In this thesis, we address these limitations by proposing methods to obtain accurate gradients through the use of a privileged value function. This approach provides valuable insights into the effectiveness of differential gradients and demonstrates that, in certain cases, it can significantly improve sim2real performance. To illustrate this, we develop an adversary that identifies the worst-case domain parameters for a given policy using local gradients. Our experiments are conducted on the Pendulum swing-up environment. This thesis forms the basis for the exploration of further possibilities of leveraging differential simulator gradients.

In the field of Artificial Intelligence (AI), techniques like Reinforcement Learning (RL) and Decision Transformer (DT) are utilized by machines to learn from experiences and solve problems. The distinction between offline and online learning determines whether the machine learns from a live environment or simply observes pre-recorded actions. The difference between single-task and multi-task settings indicates whether the machine can handle similar but not identical tasks. Multi-task, offline learning, the focus of this paper, allows machines to address a variety of related tasks, based on a pre-recorded set of experiences. This approach is particularly valuable in situations where traditional training methods are costly or challenging. For instance, in robotics, multi-task, offline learning enables robots to use experiences from various tasks, such as picking up objects, to solve new problems like placing them down. This research paper explores the effectiveness of Decision Transformers in multi-task environments through theoretical discussions and practical examples. It also tries to answer the question, of how introducing sub-optimal training data, affects the performance or generalisation ability of the model.

This paper examines the generalization capabilities of the Soft Actor-Critic (SAC) algorithm when combined with Behavioral Cloning (BC) in a MiniGrid Four-Room Environment. Reinforcement learning (RL), particularly offline, is important for tasks where interactions with the environments are risky or costly, and this research focuses on multi-task environments where generalizability to new tasks is crucial. Our findings indicate that SAC+BC can achieve generalization performance close to BC. Notably, while BC shows robustness across various dataset characteristics (quality, diversity, size), SAC alone struggles without integrating BC, highlighting the enhancement in generalization brought by this hybrid approach. Furthermore, an increased data size only enhances generalizability when introducing greater diversity. However, these results are constrained by hardware limitations, suggesting that further hyperparameter optimization and using more seeds could validate and possibly enhance our findings, demonstrating that SAC+BC is even more effective
than shown. The implementation details and the source code for this study are available on GitHub at https://github.com/AxelGeist/multi-task-offlinereinforcement-learning.

Offline Reinforcement Learning (Offline RL) involves learning policies from a static dataset without further interactions with the environment, making it suitable for high-stakes scenarios where data collection is costly or risky. This paper investigates the generalization capabilities of Implicit Q-Learning (IQL), an offline RL algorithm, compared to Behavioral Cloning (BC). We adapt the IQL algorithm for discrete control and evaluate both IQL and BC in a four-room environment using training datasets generated from different behavioral policies. Performance is assessed based on average rewards over various test seeds, on reachable and unreachable tasks, as well as the training set. Our results indicate that BC consistently outperforms IQL across all scenarios, although IQL reaches peak performance faster. This study highlights the need for further research into offline RL algorithms for better generalization and more robust performance in diverse environments. Full code available on GitHub.

Recent work has shown that offline reinforcement learning (RL) does not generalize well to new environments compared to behavioral cloning (BC). We propose WSAC-N, an ensemble model of soft actor-critics with weights to de-emphasize actions with high variance. We compare the zero-shot generalization abilities of WSAC-N with the baseline BC in a four-room maze-like environment, testing on unseen tasks. Our findings indicate that WSAC-N has worse zero-shot generalization compared to BC, aligning with previous work. Additionally, we investigate the impact of dataset characteristics on generalization, finding that dataset size has a negligible impact, while the quality of trajectories generally has a positive effect. These results are consistent with prior research.

Meta-learning is an important emerging paradigm in machine learning, aimed at improving data-efficiency and generalization performance across learning tasks. Challenges caused by noisy data has been extensively researched in traditional learning settings. However, its impact in the context of meta-learning, especially concerning label noise in meta-training, remains under-explored. Curriculum Learning (CL), is an approach where training data is ordered from easy to complex, and models learn from easier to harder samples. A type of CL , Self-Paced learning (SPL) offers adaptive data curriculum, where ordering is based on per sample model performance during training. Self-Paced Learning (SPL) has proven effective in enhancing model robustness and convergence under noisy data scenarios. However, its application in meta-learning under these conditions remains limited. In this paper, we use a Neural Process model on 1D sinusoidal function regression tasks, with different ratio of clean / noisy training data scenarios to empirically observe the same benefits SPL can potentially offer for noisy meta-learning. In line with findings in traditional learning settings, SPL improved overall training convergence, also lead to increase in generalization thus noise robustness. Furthermore SPL lead the model to be more robust to increasing scale of noise for tasks within the training data distribution.

We investigate whether a teacher-student curriculum learning approach using a teacher network with a simpler structure than the student network can achieve better results at meta-learning. The goal of meta-learning is to learn from a set of tasks, and then perform well on a new, structurally similar but unseen task with minimal retraining. Instead of sampling uniformly from all data to create the training batches, the curriculum-learning approach aims to create a sequence of mini-batches that enhances the training process, also known as a curriculum. During teacher-student curriculum learning a "teacher" network is trained in the standard manner, and then its outputs are used to order the training samples by difficulty and categorise them into mini-batches. This curriculum is then used to train the "student" network. Previous teacher-student models either had pre-trained more complex teachers, or teachers with the same structure as the student network. We investigate whether a teacher network with a simpler structure can also increase accuracy, while preserving computational resources. We find that using such a curriculum worsens performance compared to not using any curriculum at all.

Meta-Learning is an emerging field where the main challenge is to develop models capable of distilling previous experiences to efficiently learn new tasks. Curriculum Learning, a group of optimization strategies, structures data in a meaningful order which aids learning. However, the extent to which curriculum strategies can optimize the performance of meta-learners remains unclear. Here we study the separate and joint effects of a model-based (ScreenerNet) and a statistics-based (Active Bias) curriculum strategy on the training of a meta-learning model (Neural Processes) which solves 1-D function regression tasks. The findings show that ScreenerNet increases in-task accuracy and accelerates convergence, but decreases the generalization performance. Active Bias achieves mixed generalization results and significantly decreases training efficiency when trained on noisy data-sets. Combining them partially mitigates ScreenerNet's overfitting and stabilizes Active Bias' susceptibility to noise, but further research is necessary in order to achieve consistent improvements to the baseline.

Agents improve by interacting with an environment and planning. By leveraging information about what they don't know, they can learn better and faster, at least in environments that benefit from exploring. They do this by estimating the uncertainty in their predictions. There are choices for how to estimate the uncertainty, and in this work, we look at what effect this choice has on the exploration and strength of agents playing board games. We compare the effect of a source of uncertainty which perfectly tracks what the agent has seen, and a source which generalizes. We also describe the challenges associated with tuning uncertainty estimators and show what considerations have to be made when exploration is not all you need.

Reinforcement learning (RL) is a type of machine learning where a model learns by
making an observation of the current state it is in, picking out an action to execute, and
observing the reward of said action, after which it receives the next state and repeats the
cycle until it reaches its goal. The traditional online training approach allows the agent to
directly interact with the live environment, but that is not always possible due to the live
environment possibly being too dangerous or costly to train in. In cases like these offline
training, which instead trains the agent on already pre-collected datasets of previously
mentioned interactions and tries to learn a better policy than the one used for collection,
offers a viable alternative by employing Q-Learning methods like CQL. However, prior
studies, such as Mediratta et al., have suggested that Behavior Cloning (BC), a
type of imitation cloning, may outperform modern offline RL methods in the multi-task
setting, where model generalization is tested on new or similar tasks rather than the ones
trained on. Considering these results, it begs the question whether it is worthwhile to
employ modern Q-Learning methods designed to derive a better policy than the one used
to collect the data, especially when they are unable to outperform standard imitation
learning.
This study seeks to reproduce and extend these findings within a custom environment.
The results reveal that, contrary to the aforementioned report, BC does not consistently
outperform CQL. Both machine learning methods exhibit comparable performance across
datasets varying in diversity and size. Additionally, incorporating more diverse data
significantly enhances generalization performance.

This paper explores the application of evolutionary algorithms to enhance task generation for Neural Processes (NPs) in meta-learning. Meta-learning aims to develop models capable of rapid adaptation to new tasks with minimal data, a necessity in fields where data collection is costly or difficult. By integrating evolutionary strategies, we aim to enhance the efficiency and robustness of NPs. We evaluate our approach using 1-D function regression problems, where Genetic Algorithm generates diverse and challenging tasks. Our results show that the evolutionary approach improves learning efficiency and model performance, achieving lower Root Mean Squared Error (RMSE) compared to traditional methods.

In Reinforcement Learning (RL), an agent learns to make decisions by interacting with an environment and receiving feedback in the form of rewards. Multi-Task Reinforcement Learning (MTRL) extends this concept by training a single agent to perform multiple tasks simultaneously, allowing for more efficient use of resources and behavior sharing between tasks. Policy Distillation (PD) is a technique commonly used in MTRL, where policies from multiple single-task agents (teachers) are distilled into a single multi-task agent (student). This is done by merging common structure across tasks, while separating task-specific properties.

However, existing PD approaches require interactions with the environment during training. In this work, we investigate the effectiveness of PD in the offline setting, where the agent has no interaction with the environment before deployment and can only learn from previously collected data. Through a series of experiments, we demonstrate that a straightforward approach yields the highest performance. This approach involves first learning teacher policies using an existing offline RL algorithm, then distilling these policies into a student by sampling states from the offline data and applying a Mean Squared Error (MSE) loss between the teachers’ and student’s best actions. Moreover, we investigate the effect of a state distribution shift—a major challenge in offline RL—on our approach. We find that such shifts impact performance only slightly in cases of relatively small neural networks or substantial distribution shifts.

We also explore how PD can be enhanced to better capture common structure across related tasks, a key to improving efficiency in MTRL. To this end, we formally define common structure at two levels: the trajectory level and the computational level. To the best of our knowledge, we present the first attempt to quantify the amount of common structure shared across tasks. This measurement reveals that task commonalities are not fully exploited automatically. At the computational level, we attempt to improve sharing of common structure by reducing the network size and adding a regularization term to the loss function. To capture more common structure at the trajectory level, we argue that multi-task exploration is required, meaning that behaviors from one task must be evaluated in the context of another task. We propose two extensions to our approach that introduce multi-task exploration: Data Sharing (DS) and Offline Q-Switch (OQS). While these extensions are capable of improving performance, they also have clear limitations.

Overall, we propose a new, high-performing offline MTRL method and provide valuable insights into the fundamental capabilities and limitations of PD in capturing common structure across tasks, specifically within the offline MTRL setting.

This research paper aims to investigate the effect of entropy while training the agent on the robustness of the agent. This is important because robustness is defined as the agent's adaptability to different environments. A self-driving car should adapt to every environment that it is being used in since a mistake could cost someone's life. Therefore, robustness is of great importance in self-driving cars. An increase in entropy would promote the exploration of different strategies and prevent convergence on local maximum results. In order to test entropy values in training, the Soft-Actor Critic algorithm is used. The algorithm is run on a simulated city environment called Carla. In the end, collected data shows that the agent which is trained with a higher entropy value adapts to environments it did not train on better than the low entropy agent. However, a low entropy agent performs better in the environment it is trained in. Therefore, increasing the entropy increases robustness but it lowers the performance in the training environment itself.

Bayesian optimisation is a rapidly growing area of research that aims to identify the optimum of the black-box function, as it strategically directs the optimisation process towards promising regions. This paper provides an overview of the theoretical background used by the Entropy Search algorithms under study, mainly Predictive Entropy Search, Max-Value Entropy Search, and Joint Entropy Search. Furthermore, we empirically analyse the performance and sensitivity of the algorithms in different environment settings. In particular, we discuss the impact of function shape, batch size, noise level, and the number of input dimensions on the final simple regret metric. The results show the weak spots of the information-theoretic methods. However, the algorithms perform better for batch optimisation, demonstrating the advantage when considering the information on the maximum function value.

Reinforcement Learning (RL) has gained atten-tion as a way of creating autonomous agents for self-driving cars. This paper explores the adap- tation of the Deep Q Network (DQN), a popular deep RL algorithm, in the Carla traffic simulator for autonomous driving. It investigates the influ- ence of action space discretization and DQN ex-
tensions on training performance and robustness. Results show that action space discretization en- hances behaviour consistency but negatively af- fects Q-values, training performance, and robust- ness. Double Q-Learning decreases training per- formance and leads to suboptimal convergence, re- ducing robustness. Prioritized Experience Replay
also performs worse during training, but consis-tently outperforms in robustness testing, reward es-timation and generalization.

Autonomous driving is a rapidly evolving field that aims to enhance road safety and reduce accidents through the use of advanced software and hardware technologies. Reinforcement learning (RL) combined with deep neural networks has emerged as a promising approach for training autonomous agents. This research paper investigates three exploration algorithms —Epsilon-Greedy, Random Network Distillation (RND), and Bootstrapped Deep Q-Network (DQN)— within the context of autonomous driving. Performance is assessed based on episodic returns in training and testing environments, as well as the time required to train the networks. The results show significant improvement in learning capability using Bootstrapped DQN without critical differences in training time. There also exists a potential to increase episodic returns further given an increase in the number of steps to train the models.

Deep reinforcement learning has been a topic of research in recent years and has been expanding into the domain of autonomous driving. As autonomous driving is likely to involve people, such as daily commuters, it is necessary to ensure the machine will perform well enough in real-life environments not to put anyone at risk. There exist possible approaches to make the transition from a simulation to real life easier, such as domain randomization. This paper uses OpenAI's CarRacing-v2 environment and the CARLA simulator to investigate the effect of domain randomization on training efficiency and robustness for a Deep Q-Network algorithm for autonomous driving. The results show a decrease in training efficiency and higher variance during training for both environments. CARLA also indicates an overestimation during training. As for robustness testing, while visual domain randomization in CarRacing-v2 does not suggest a significant influence on robustness, the dynamic domain randomization in CARLA offers a positive influence toward robustness at the expense of some reward.

Bayesian Optimization (BO) has demonstrated significant utility across numerous applications. However, due to it being designed as a universal optimizer, its performance can often be suboptimal in specialized environments. To overcome this issue, research has been conducted into the application of transfer learning for enhancing BO performance in these specialized contexts. This paper describes the research done into evaluating the MetaBO algorithm in some specific environments. MetaBO innovates by substituting the acquisition function component in BO with a neural network that serves as an acquisition function, trained via a reinforcement learning framework. Although the results indicate that the algorithm's performance is not optimal in the environments tested, these limitations are ascribed to elements of the implementation rather than the concept of the algorithm itself. Consequently, further research is necessary to refine the implementation process and fully exploit the potential of the MetaBO algorithm.

Autonomous driving is a complex problem that can potentially be solved using artificial intelligence. The complexity stems from the system's need to understand the surroundings and make appropriate decisions. However, there are various challenges in constructing such a sophisticated system. One of the main challenges is to make the agent learn from the environmental input and since the environment is not fully observable and constantly changing, the agent should be flexible enough to extract important information from the input. To create such an agent this paper focused on the 3 different methods, specifically the application of frame stacking, long short-term memory (LSTM), and a combination of both methods. To analyze these methods 3 Deep Q Network(DQN) based agents are created. These 3 agents have frame stacking, LSTM, and both combined methods to solve the partially observable problem of autonomous driving. Their training performances are analyzed, and the results revealed significantly different trends in the training and evaluation phase.
Especially the experiment resulted in LSTM being a more robust method but had lower performance than DQN with frame stack, which showed a trade-off between these 2 qualities of an agent. The agent with LSTM and frame stack was able to learn faster at the beginning, but as it was unstable, it got a lower return value from the training run at the end. This instability can be a problem in the real world, especially in autonomous driving, where it is very important to have robust implementation.

Scientific problems are often concerned with optimization of control variables of complex systems, for instance hyperparameters of machine learning models. A popular solution for such intractable environments is Bayesian optimization. However, many implementations disregard dynamic evaluation costs associated with the optimization procedure. Furthermore, another common trope among
Bayesian algorithms is that they are short-sighted and do not consider long-term effects of their actions. This paper investigates the viability of multitimestep cost-aware Bayesian optimizers and evaluates their performance in environments with delayed rewards. To this end, we combine existing works on parallel Bayesian optimizers and costaware heuristics. Our findings reveal that although
such parallel optimizers yield more optimal results and are more resistant to delayed feedback compared to their myopic counterparts, they are unable to achieve cost-awareness.