README.md

REINFORCE Algorithm Training Results

Total Rewards Across Episodes

Episode	Total Reward
1	25.0
2	14.0
3	11.0
4	36.0
5	15.0
6	23.0
7	11.0
8	20.0
9	24.0
10	11.0
11	11.0
12	10.0
13	35.0
14	26.0
15	26.0
16	36.0
17	31.0
18	16.0
19	23.0
20	28.0
21	15.0
22	24.0
23	18.0
24	38.0
25	48.0
26	11.0
27	25.0
28	65.0
29	41.0
30	15.0
31	27.0
32	19.0
33	54.0
34	21.0
35	48.0
36	113.0
37	38.0
38	51.0
39	19.0
40	37.0
41	27.0
42	50.0
43	65.0
44	22.0
45	50.0
46	13.0
47	58.0
48	14.0
49	29.0
50	83.0
51	60.0
52	34.0
53	124.0
54	25.0
55	73.0
56	167.0
57	11.0
58	23.0
59	26.0
60	30.0
61	33.0
62	86.0
63	184.0
64	89.0
65	69.0
66	82.0
67	91.0
68	56.0
69	29.0
70	83.0
71	96.0
72	124.0
73	84.0
74	95.0
75	119.0
76	70.0
77	195.0
78	26.0
79	71.0
80	26.0
81	90.0
82	96.0
83	87.0
84	81.0
85	77.0
86	85.0
87	106.0
88	93.0
89	122.0
90	15.0
91	120.0
92	174.0
93	107.0
94	73.0
95	40.0
96	203.0
97	165.0
98	110.0
99	79.0
100	127.0
101	66.0
102	55.0
103	41.0
104	129.0
105	158.0
106	182.0
107	206.0
108	165.0
109	127.0
110	173.0
111	158.0
112	136.0
113	120.0
114	110.0
115	69.0
116	163.0
117	243.0
118	157.0
119	186.0
120	132.0
121	298.0
122	107.0
123	280.0
124	105.0
125	219.0
126	67.0
127	194.0
128	233.0
129	189.0
130	101.0
131	245.0
132	122.0
133	218.0
134	108.0
135	466.0
136	159.0
137	198.0
138	240.0
139	162.0
140	216.0
141	130.0
142	349.0
143	387.0
144	108.0
145	309.0
146	64.0
147	234.0
148	151.0
149	86.0
150	219.0
151	210.0
152	500.0
153	201.0
154	250.0
155	272.0
156	263.0
157	207.0
158	146.0
159	122.0
160	99.0
161	213.0
162	138.0
163	139.0
164	270.0
165	140.0
166	259.0
167	113.0
168	148.0
169	311.0
170	136.0
171	292.0
172	307.0
173	240.0
174	267.0
175	124.0
176	124.0
177	163.0
178	290.0
179	91.0
180	265.0
181	145.0
182	151.0
183	257.0
184	290.0
185	138.0
186	204.0
187	320.0
188	90.0
189	100.0
190	161.0
191	170.0
192	147.0
193	134.0
194	206.0
195	144.0
196	155.0
197	151.0
198	149.0
199	151.0
200	138.0
201	192.0
202	175.0
203	210.0
204	130.0
205	100.0
206	225.0
207	119.0
208	84.0
209	163.0
210	138.0
211	242.0
212	253.0
213	250.0
214	253.0
215	356.0
216	311.0
217	273.0
218	175.0
219	273.0
220	103.0
221	91.0
222	147.0
223	111.0
224	114.0
225	86.0
226	104.0
227	65.0
228	126.0
229	131.0
230	71.0
231	67.0
232	63.0
233	120.0
234	112.0
235	58.0
236	82.0
237	60.0
238	174.0
239	92.0
240	90.0
241	100.0
242	186.0
243	108.0
244	158.0
245	206.0
246	165.0
247	264.0
248	224.0
249	353.0
250	500.0
251	165.0
252	363.0
253	180.0
254	408.0
255	261.0
256	259.0
257	253.0
258	205.0
259	151.0
260	170.0
261	136.0
262	176.0
263	86.0
264	132.0
265	82.0
266	229.0
267	196.0
268	185.0
269	168.0
270	238.0
271	216.0
272	196.0
273	204.0
274	114.0
275	152.0
276	281.0
277	258.0
278	239.0
279	236.0
280	215.0
281	236.0
282	228.0
283	241.0
284	91.0
285	248.0
286	138.0
287	238.0
288	204.0
289	228.0
290	242.0
291	102.0
292	260.0
293	197.0
294	318.0
295	265.0
296	336.0
297	209.0
298	134.0
299	281.0
300	331.0
301	276.0
302	394.0
303	357.0
304	368.0
305	406.0
306	293.0
307	148.0
308	438.0
309	500.0
310	500.0
311	314.0
312	500.0
313	395.0
314	438.0
315	474.0
316	418.0
317	500.0
318	500.0
319	407.0
320	500.0
321	500.0
322	500.0
323	500.0
324	500.0
325	500.0
326	500.0
327	500.0
328	500.0
329	247.0
330	500.0
331	500.0
332	500.0
333	500.0
334	500.0
335	500.0
336	500.0
337	500.0
338	500.0
339	500.0
340	500.0
341	500.0
342	500.0
343	400.0
344	500.0
345	500.0
346	260.0
347	500.0
348	493.0
349	302.0
350	343.0
351	500.0
352	239.0
353	500.0
354	299.0
355	137.0
356	393.0
357	429.0
358	278.0
359	346.0
360	333.0
361	279.0
362	328.0
363	122.0
364	270.0
365	249.0
366	181.0
367	329.0
368	321.0
369	424.0
370	322.0
371	317.0
372	324.0
373	431.0
374	254.0
375	389.0
376	444.0
377	203.0
378	422.0
379	329.0
380	500.0
381	500.0
382	500.0
383	500.0
384	500.0
385	500.0
386	500.0
387	500.0
388	500.0
389	500.0
390	500.0
391	500.0
392	500.0
393	500.0
394	500.0
395	500.0
396	500.0
397	500.0
398	500.0
399	500.0
400	500.0
401	500.0
402	500.0
403	500.0
404	500.0
405	500.0
406	500.0
407	500.0
408	500.0
409	500.0
410	500.0
411	500.0
412	500.0
413	500.0
414	359.0
415	500.0
416	500.0
417	500.0
418	500.0
419	459.0
420	456.0
421	330.0
422	287.0
423	284.0
424	311.0
425	273.0
426	314.0
427	235.0
428	269.0
429	330.0
430	303.0
431	270.0
432	356.0
433	294.0
434	287.0
435	236.0
436	306.0
437	243.0
438	122.0
439	225.0
440	247.0
441	216.0
442	192.0
443	227.0
444	242.0
445	181.0
446	308.0
447	115.0
448	225.0
449	292.0
450	194.0
451	318.0
452	343.0
453	292.0
454	444.0
455	488.0
456	500.0
457	289.0
458	423.0
459	469.0
460	500.0
461	413.0
462	500.0
463	500.0
464	500.0
465	500.0
466	500.0
467	500.0
468	500.0
469	500.0
470	500.0
471	500.0
472	500.0
473	500.0
474	500.0
475	500.0
476	500.0
477	399.0
478	500.0
479	246.0
480	500.0
481	500.0
482	500.0
483	500.0
484	500.0
485	500.0
486	500.0
487	240.0
488	219.0
489	359.0
490	500.0
491	349.0
492	332.0
493	318.0
494	414.0
495	215.0
496	347.0
497	117.0
498	359.0
499	259.0
500	402.0

Evaluation Results

Success rate over 100 evaluations: 100.00%

CartPole Solved with A2C

Trained using Stable-Baselines3 with the Advantage Actor-Critic (A2C) algorithm. Success rate over 100 evaluations: 100.00%

CartPole Solved with A2C

Trained using Stable-Baselines3 with the Advantage Actor-Critic (A2C) algorithm. Success rate over 100 evaluations: 100.00%

REINFORCE CartPole Model on Hugging Face Hub

Click here to view and download the trained model

CartPole Training with A2C on Weights & Biases

View the training run on Weights & Biases

PandaReachJointsDense-v3 Training with A2C

View the training run on Weights & Biases Download the trained model on Hugging Face Hub