The film was criticized by the LGBT community of Kerala for its distorted portrayal of gender and sexuality. Valsala Menon as Freddy's and Rosie's grandmother.Shobha Mohan as Shantha, Radhakrishnan's mother.Sukumari as Radhakrishnan's grandmother.Lal as Divakaran, Radhakrishnan's father.When Radha sees the child, he vows to raise it as a boy, ripping off the ribbon tied to its hair. In the meantime, Malu prematurely gives birth to Radha's child. Towards the end of the fight, Radha defeats Kumaran and is about to kill him but, reminded of how his father had to suffer in jail due to murder charges, he spares Kumaran. His arrival follows a fight with Kumaran. He also learns that Malu is pregnant with Radha's child. On reaching his native shore, he discovers that his family, along with his house was brutally burned down by Kumaran. Radha is forced to return to his home to escape from the police. During the fight, Cleetus gets severely injured on the head. Once, he gets involved in a fight with Cleetus, an old enemy of Freddy, after Cleetus tries to molest Rosie. With a change in environment, he also changes his behaviour, adopting more traditionally male mannerisms. He soon becomes a part of their family, as the grandmother begins to identify him as the late Jonfy. Freddy takes him to the former's native where he is living with his sister Rosie and his grandmother, who is a mental patient due to the shock of the sudden death of Freddy's other sibling, Jonfy. But he is saved by Freddy, a restaurant owner, in some distant shore. Slowly Radha's liking for Malu turns into love and when Kumaran sees it, he beats up Radha with the help of her father, a local astrologer and dumps him in deep sea by saying he is a curse to the shore.
His best friend is Malu who is wooed by Kumaran, a local money lender and the son of the man whom Radha's father had killed in a fight after Kumaran insults Radha for behaving like girl.ĭivakaran comes back from jail and dislikes his son's mannerisms, but can do nothing about them. Radha is ridiculed among the people in the village as he is considered effeminate, but he is not worried and spends time with the girls singing and teaches dancing. Radha's father Divakaran goes to jail for a murder that he accidentally commits. She calls him Radha, which becomes his nickname. The experiment indicates that the MME approach sets out to be in the present paper effectively avoids the deceptive reward trap and learns the global optimal strategy.Radhakrishnan is brought up like a girl by his grandmother who wanted a granddaughter. We conduct experiments comparing our approach with state-of-the-art deep reinforcement learning algorithm and exploration methods in the grid world and StarCraft II environments with deceptive reward. An on-policy mode switch trick is used to validly prevent the unstable and diverge which caused by the deadly triad. To alleviate the catastrophic forgetting problem which leads to the training of the agent not stabilized during the off-policy exploration phrase, the optimal experience replay is applied. The target policy regards the maximization of external reward as the optimization goal to achieve the global solution. The explorer policy, taking the maximum entropy of the target policy as the optimization goal, is used to interact with the environment and generated trajectories for the target policy. Based on entropy rewards and the off-policy actor-critic reinforcement learning algorithm, we divided the agent exploration policy into two independent parts, namely, the target policy and the explorer policy. To address this shortfall, we introduce a further exploration approach called Maximum Entropy Explore (MEE). Most of the cutting-edge exploration approaches, such as count-based and curiosity-driven, even with intrinsic motivation, which achieves better performance in the sparse reward game, still easily fall into local optimal traps in the deceptive game. Deceptive games are games that utilize the reward structure to keep the agent away from the global optimization and have been grown up to become a huge challenge in the field of deep reinforcement learning intelligent exploration.
0 kommentar(er)
