Autonomous Agents in Snake Game via Deep Reinforcement Learning

Wei, Zhepei; Wang, Di; Zhang, Ming; Tan, Ah-Hwee; Miao, Chunyan

doi:10.1109/agents.2018.8460004

Cited by 13 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DQN was initially presented by DeepMind (2013) ( Jiang et al, 2021a ) to play the Atari video game, and it successfully learned the control policy and remarkably outperformed human-level performance. Excellent as DQN may seem, adjustments are still required when it is applied to other game scenarios such as the design of reward systems and the adoption of replay buffers (2018) ( Wei et al, 2018 ).…”

Section: Implementation Of Deep Reinforcement Learning Methods For Do...mentioning

confidence: 99%

“…Value-based, policy gradient, and model-based DRL methods are applied to various video games such as Atari, Minecraft, and StarCraft. For example, Wei et al (2018) employed convolutional neural networks trained with refined DQN to play the snake game. DRL has been a long-standing research area when it comes to artificial intelligence in differential games.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Pursuit and Evasion Strategy of a Differential Game Based on Deep Reinforcement Learning

Zhang

Wang

et al. 2022

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

Since the emergence of deep neural network (DNN), it has achieved excellent performance in various research areas. As the combination of DNN and reinforcement learning, deep reinforcement learning (DRL) becomes a new paradigm for solving differential game problems. In this study, we build up a reinforcement learning environment and apply relevant DRL methods to a specific bio-inspired differential game problem: the dog sheep game. The dog sheep game environment is set on a circle where the dog chases down the sheep attempting to escape. According to some presuppositions, we are able to acquire the kinematic pursuit and evasion strategy. Next, this study implements the value-based deep Q network (DQN) model and the deep deterministic policy gradient (DDPG) model to the dog sheep game, attempting to endow the sheep the ability to escape successfully. To enhance the performance of the DQN model, this study brought up the reward mechanism with a time-out strategy and the game environment with an attenuation mechanism of the steering angle of sheep. These modifications effectively increase the probability of escape for the sheep. Furthermore, the DDPG model is adopted due to its continuous action space. Results show the modifications of the DQN model effectively increase the escape probabilities to the same level as the DDPG model. When it comes to the learning ability under various environment difficulties, the refined DQN and the DDPG models have bigger performance enhancement over the naive evasion model in harsh environments than in loose environments.

show abstract

Section: Implementation Of Deep Reinforcement Learning Methods For Do...mentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Pursuit and Evasion Strategy of a Differential Game Based on Deep Reinforcement Learning

Zhang

Wang

et al. 2022

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

show abstract

“…We tried to keep the mechanism as smooth and continuous as possible and provided rewards within a certain scale. 22 One of the reward mechanisms that were successful is shown in Listing 2. Some states such as "parking_completed", "getting_close_to_park" are only active for the agent † The Python source code of the simulation environment (used for Deep Q-Learning) is available at: https://github.com/AlicanOzeloglu/car-simulation.…”

Section: Simulationmentioning

confidence: 99%

Deep reinforcement learning‐based autonomous parking design with neural network compute accelerators

Özeloğlu

Gürbüz

San

2021

Concurrency and Computation

View full text Add to dashboard Cite

We describe the design and implementation of an autonomous prototype vehicle which finds an empty parking slot in a parking area, and parks itself in the empty parking slot, using neural networks based on deep reinforcement learning (RL). To perform an autonomous parking procedure for our prototype vehicle, two different artificial neural networks (ANNs) are trained using a deep RL Algorithm in a simulation environment and embedded into the computing platform of the prototype car.One of the ANNs enables the vehicle to drive autonomously in the parking environment. At the same time, an image processing algorithm is used to determine whether a parking slot is empty. When the image processing algorithm finds a suitable parking slot, a different ANN is activated and performs a safe parking procedure. However, ANN-based machine learning techniques require high processing power and impose a high computational burden on embedded CPU and GPU platforms. To alleviate the computational burden, one can achieve higher performance and less power consumption using an application-specific hardware design, where logic resources are fully exploited according to the algorithm of interest, in an energy-efficient manner. In this article, hardware accelerators for our ANN models are designed and generated via the Vivado high-level synthesis (HLS) tool, targeting an ARM based programmable SoC platform, ZedBoard. Our ANN accelerators have achieved a speedup of 17x as compared to an ARM software implementation. For deeper fully-connected layers used in deep RL-based solutions, function-level parallelism (Vivado's dataflow) is employed to improve the computational efficiency. Our proposed stage-level description for fully connected layers outperforms recent studies in terms of computation time.

show abstract

“…To incorporate the quality of the experiences during sampling, various experience replay techniques, such as prioritized (Schaul et al 2015), hindsight (Andrychowicz et al 2017) and dual (Wei et al 2018), have been proposed in the literature. Nonetheless, these extended strategies are built upon purely goal-orientated mechanisms, without any neurocognitive basis.…”

Section: Related Workmentioning

confidence: 99%

Modelling Autobiographical Memory Loss across Life Span

Wang

Tan

Miao

et al. 2019

AAAI

Self Cite

View full text Add to dashboard Cite

Neurocomputational modelling of long-term memory is a core topic in computational cognitive neuroscience, which is essential towards self-regulating brain-like AI systems. In this paper, we study how people generally lose their memories and emulate various memory loss phenomena using a neurocomputational autobiographical memory model. Specifically, based on prior neurocognitive and neuropsychology studies, we identify three neural processes, namely overload, decay and inhibition, which lead to memory loss in memory formation, storage and retrieval, respectively. For model validation, we collect a memory dataset comprising more than one thousand life events and emulate the three key memory loss processes with model parameters learnt from memory recall behavioural patterns found in human subjects of different age groups. The emulation results show high correlation with human memory recall performance across their life span, even with another population not being used for learning. To the best of our knowledge, this paper is the first research work on quantitative evaluations of autobiographical memory loss using a neurocomputational model.

show abstract

Autonomous Agents in Snake Game via Deep Reinforcement Learning

Cited by 13 publications

References 12 publications

Pursuit and Evasion Strategy of a Differential Game Based on Deep Reinforcement Learning

Pursuit and Evasion Strategy of a Differential Game Based on Deep Reinforcement Learning

Deep reinforcement learning‐based autonomous parking design with neural network compute accelerators

Modelling Autobiographical Memory Loss across Life Span

Contact Info

Product

Resources

About