Simulation environments are good for learning different driving tasks like lane changing, parking or handling intersections etc. in an abstract manner. However, these simulation environments often restrict themselves to operate under conservative interactions behavior amongst different vehicles. But, as we know that the real driving tasks often involves very high risk scenarios where other drivers often don't behave in the expected sense. There can be many reasons for this behavior like being tired or inexperienced. The simulation environments doesn't take this information into account while training the navigation agent. Therefore, in this study we especially focus on systematically creating these risk prone scenarios with heavy traffic and unexpected random behavior for creating better model-free learning agents. We generate multiple autonomous driving scenarios by creating new custom Markov Decision Process (MDP) environment iterations in highway-env simulation package. The behavior policy is learnt by agents trained with the help from deep reinforcement learning models. Our behavior policy is deliberated to handle collisions and risky randomized driver behavior. We train model free learning agents with supplement information of risk prone driving scenarios and compare their performance with baseline agents. Finally, we casually measure the impact of adding these perturbations in the training process to precisely account for the performance improvement attained from utilizing the learnings from these scenarios.

Deploying Reinforcement Learning (RL) agents in the real-world require that the agents satisfy safety constraints. Current RL agents explore the environment without considering these constraints, which can lead to damage to the hardware or even other agents in the environment. We propose a new method, LBPO, that uses a Lyapunov-based barrier function to restrict the policy update to a safe set for each training iteration. Our method also allows the user to control the conservativeness of the agent with respect to the constraints in the environment. LBPO significantly outperforms state-of-the-art baselines in terms of the number of constraint violations during training while being competitive in terms of performance. Further, our analysis reveals that baselines like CPO and SDDPG rely mostly on backtracking to ensure safety rather than safe projection, which provides insight into why previous methods might not have effectively limit the number of constraint violations.

Abstract-- Deep reinforcement Learning for end-to-end driving is limited by the need of complex reward engineering. Sparse rewards can circumvent this challenge but suffers from long training time and leads to sub-optimal policy. In this work, we explore driving using only goal conditioned sparse rewards and propose a curriculum learning approach for end to end driving using only navigation view maps that benefit from small virtual-to-real domain gap. To address the complexity of multiple driving policies, we learn concurrent individual policies which are selected at inference by a navigation system. Figure 1: End to End Driving. Performance of Deep RL in competing with humans in games like Atari [32], AlphaGo [46] and Dota [2] has shown its potential to solve complex decision making problems for navigation decision at intersections (e.g.

Reward shaping (RS) is a powerful method in reinforcement learning (RL) for overcoming the problem of sparse and uninformative rewards. However, RS relies on manually engineered shaping-reward functions whose construction is typically time-consuming and error-prone. It also requires domain knowledge which runs contrary to the goal of autonomous learning. In this paper, we introduce an automated RS framework in which the shaping-reward function is constructed in a novel stochastic game between two agents. One agent learns both which states to add shaping rewards and their optimal magnitudes and the other agent learns the optimal policy for the task using the shaped rewards. We prove theoretically that our framework, which easily adopts existing RL algorithms, learns to construct a shaping-reward function that is tailored to the task and ensures convergence to higher performing policies for the given task. We demonstrate the superior performance of our method against state-of-the-art RS algorithms in Cartpole and the challenging console games Gravitar, Solaris and Super Mario.

We aim to investigate the potential impacts of smart homes on human behavior. To this end, we simulate a series of human models capable of performing various activities inside a reinforcement learning-based smart home. We then investigate the possibility of human behavior being altered as a result of the smart home and the human model adapting to one-another. We design a semi-Markov decision process human task interleaving model based on hierarchical reinforcement learning that learns to make decisions to either pursue or leave an activity. We then integrate our human model in the smart home which is based on Q-learning. We show that a smart home trained on a generic human model is able to anticipate and learn the thermal preferences of human models with intrinsic rewards similar to the generic model. The hierarchical human model learns to complete each activity and set optimal thermal settings for maximum comfort. With the smart home, the number of time steps required to change the thermal settings are reduced for the human models. Interestingly, we observe that small variations in the human model reward structures can lead to the opposite behavior in the form of unexpected switching between activities which signals changes in human behavior due to the presence of the smart home.

Now, let's say these doctors want to design another algorithm to recommend treatment plans. Since these plans will be implemented in stages, and they may change depending on each individual's response to treatments, the doctors decide to use reinforcement learning. This program uses an iterative approach to gather feedback about which medications, dosages and treatments are most effective. Then, it compares that data against each patient's profile to create their unique, optimal treatment plan. As the treatments progress and the program receives more feedback, it can constantly update the plan for each patient.

The recent remarkable progress of deep reinforcement learning (DRL) stands on regularization of policy for stable and efficient learning. A popular method, named proximal policy optimization (PPO), has been introduced for this purpose. PPO clips density ratio of the latest and baseline policies with a threshold, while its minimization target is unclear. As another problem of PPO, the symmetric threshold is given numerically while the density ratio itself is in asymmetric domain, thereby causing unbalanced regularization of the policy. This paper therefore proposes a new variant of PPO by considering a regularization problem of relative Pearson (RPE) divergence, so-called PPO-RPE. This regularization yields the clear minimization target, which constrains the latest policy to the baseline one. Through its analysis, the intuitive threshold-based design consistent with the asymmetry of the threshold and the domain of density ratio can be derived. Through four benchmark tasks, PPO-RPE performed as well as or better than the conventional methods in terms of the task performance by the learned policy.

In many robotic tasks, such as drone racing, the goal is to travel through a set of waypoints as fast as possible. A key challenge for this task is planning the minimum-time trajectory, which is typically solved by assuming perfect knowledge of the waypoints to pass in advance. The resulting solutions are either highly specialized for a single-track layout, or suboptimal due to simplifying assumptions about the platform dynamics. In this work, a new approach to minimum-time trajectory generation for quadrotors is presented. Leveraging deep reinforcement learning and relative gate observations, this approach can adaptively compute near-time-optimal trajectories for random track layouts. Our method exhibits a significant computational advantage over approaches based on trajectory optimization for non-trivial track configurations. The proposed approach is evaluated on a set of race tracks in simulation and the real world, achieving speeds of up to 17 m/s with a physical quadrotor.

Generally, when learners are now studying the knowledge of the reinforcement learning algorithm at the beginning, the algorithm we first came up in learner's mind is the Q-learning algorithm, which is a classical reinforcement learning algorithm based on value iteration. In the state-to-action mapping process, an algorithm based on value iteration allows the system to explore in accordance with the policy guidelines, and update the state value at each step of the exploration. Then, in value-based iteration, we have several problems that cannot prevent that. For example, when the value of each state is updated, it is necessary to estimate the probability of all actions. Unlike the discrete action of walking a maze, some cases such as robot control and automatic driving since the massive state information brought by continuous actions makes the calculation process almost impossible by tabular computation. At this time, Policy Gradient, a reinforcement learning algorithm based on iteration policy, came into being. The policy gradient no longer calculates the reward, but directly calculates the probability of taking an action in a certain state, and directly selects the action through the probability.

Developing an agent in reinforcement learning (RL) that is capable of performing complex control tasks directly from high-dimensional observation such as raw pixels is yet a challenge as efforts are made towards improving sample efficiency and generalization. This paper considers a learning framework for Curiosity Contrastive Forward Dynamics Model (CCFDM) in achieving a more sample-efficient RL based directly on raw pixels. CCFDM incorporates a forward dynamics model (FDM) and performs contrastive learning to train its deep convolutional neural network-based image encoder (IE) to extract conducive spatial and temporal information for achieving a more sample efficiency for RL. In addition, during training, CCFDM provides intrinsic rewards, produced based on FDM prediction error, encourages the curiosity of the RL agent to improve exploration. The diverge and less-repetitive observations provide by both our exploration strategy and data augmentation available in contrastive learning improve not only the sample efficiency but also the generalization. Performance of existing model-free RL methods such as Soft Actor-Critic built on top of CCFDM outperforms prior state-of-the-art pixel-based RL methods on the DeepMind Control Suite benchmark.