Deep-Reinforcement-Learning-Algorithms-with-PyTorch
Deep-Reinforcement-Learning-Algorithms-with-PyTorch copied to clipboard
p-christ
PyTorch implementations of deep reinforcement learning algorithms and environments
HI！Does this library support multi-dimensional action space?
I'm wondering if the loss of discriminator in GAIL could be "discrim_loss = discrim_criterion(g_o, zeros((states.shape[0], 1), device=device)) + \ discrim_criterion(e_o, ones((expert_traj.shape[0], 1), device=device))" instead of "discrim_loss = discrim_criterion(g_o, ones((states.shape[0], 1),...
Hi p-christ, Thanks for this amazing contribution. Recently, I tried the implementation of DDPG for MountainCar (with default parameters in results/Mountain_Car.py). However, the results are quite different from the plot...
README file should have git clone link replaced with https://github.com/p-christ/Deep-Reinforcement-Learning-Algorithms-with-PyTorch.git
I tried to run the script from `results/Mountain_Car.py,` but I ran into an error, ``` Traceback (most recent call last): File "Mountain_Car.py", line 3, in from agents.policy_gradient_agents.PPO import PPO ModuleNotFoundError:...
I have a question regarding the method `reset_game` in Base_Agent. The first few lines read: ``` def reset_game(self):Calling seed """Resets the game information so we are ready to play a...
There is no implementation of a function update_next_state_reward_done_and_score() in REINFORCE agent.
I run the Cart_Pole.py with A3C&A2C on windows and got the error. Traceback (most recent call last): File "D:/学习/Deep-Reinforcement-Learning-Algorithms-with-PyTorch-master/results/Cart_Pole.py", line 142, in trainer.run_games_for_agents() File "D:\学习\Deep-Reinforcement-Learning-Algorithms-with-PyTorch-master\agents\Trainer.py", line 79, in run_games_for_agents self.run_games_for_agent(agent_number...
In agents/Base_Agent.py ``` def print_rolling_result(self): """Prints out the latest episode results""" text = """"\r Episode {0}, Score: {3: .2f}, Max score seen: {4: .2f}, Rolling score: {1: .2f}, Max rolling...
I tried Pong game from atari. It returns the error ``` AttributeError: 'AtariEnv' object has no attribute 'reward_threshold' ``` I check `get_score_required_to_win` in `Base_Agent.py`. I wonder can I set `return...
